From 0e6a288458640f4499e646c1d0ad445c14a85bfb Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:04:16 -0700 Subject: [PATCH 01/11] fix(ssrf): point the blocked-address remediation at litellm_settings (#42508) * fix(ssrf): point the blocked-address remediation at litellm_settings Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(ssrf): pin the block message's named section to litellm_settings Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(compaction): pin litellm.max_budget so leaked proxy budget cannot 401 the child auth Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: shivam Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../prompt_templates/image_handling.py | 2 +- litellm/litellm_core_utils/url_utils.py | 2 +- .../litellm_core_utils/test_image_handling.py | 2 +- .../proxy/proxy_server/test_proxy_config.py | 28 +++++++++++++++++++ .../proxy/test_native_compaction.py | 2 ++ 5 files changed, 33 insertions(+), 3 deletions(-) diff --git a/litellm/litellm_core_utils/prompt_templates/image_handling.py b/litellm/litellm_core_utils/prompt_templates/image_handling.py index c9933422cc3..c44c80bc0a0 100644 --- a/litellm/litellm_core_utils/prompt_templates/image_handling.py +++ b/litellm/litellm_core_utils/prompt_templates/image_handling.py @@ -82,7 +82,7 @@ def _rejected_image_fetch(url: str, verdict: SSRFError) -> "litellm.ImageFetchEr verbose_logger.warning("Image fetch of %s rejected before any request went out: %s", url, verdict) return litellm.ImageFetchError( "Error: Unable to fetch image from URL. The proxy could not resolve this host or its URL policy rejected it; " - f"an admin can check the proxy log and `user_url_allowed_hosts` in general_settings. url={url}" + f"an admin can check the proxy log and `user_url_allowed_hosts` in litellm_settings. url={url}" ) diff --git a/litellm/litellm_core_utils/url_utils.py b/litellm/litellm_core_utils/url_utils.py index b94d5a6886d..6c87ef4a3de 100644 --- a/litellm/litellm_core_utils/url_utils.py +++ b/litellm/litellm_core_utils/url_utils.py @@ -336,7 +336,7 @@ def validate_url(url: str) -> tuple[str, str]: raise SSRFError( f"URL targets a blocked address ({resolved_ip}). " "If this is a legitimate internal service, add the host " - "to `user_url_allowed_hosts` in general_settings." + "to `user_url_allowed_hosts` in litellm_settings." ) # For HTTPS with SSL verification enabled, TLS certificate validation diff --git a/tests/test_litellm/litellm_core_utils/test_image_handling.py b/tests/test_litellm/litellm_core_utils/test_image_handling.py index 8fa4bd6c14d..21e97e97357 100644 --- a/tests/test_litellm/litellm_core_utils/test_image_handling.py +++ b/tests/test_litellm/litellm_core_utils/test_image_handling.py @@ -427,7 +427,7 @@ async def test_async_inline_remote_media_cancels_the_other_fetches_when_one_fail _SSRF_VERDICTS = ( SSRFError( "URL targets a blocked address (10.0.0.8). If this is a legitimate internal service, " - "add the host to `user_url_allowed_hosts` in general_settings." + "add the host to `user_url_allowed_hosts` in litellm_settings." ), SSRFError("DNS resolution failed for 'internal.example': [Errno 8] nodename nor servname provided, or not known"), SSRFError("No addresses found for 'internal.example'"), diff --git a/tests/test_litellm/proxy/proxy_server/test_proxy_config.py b/tests/test_litellm/proxy/proxy_server/test_proxy_config.py index 832ac6402d9..b47cce43dcc 100644 --- a/tests/test_litellm/proxy/proxy_server/test_proxy_config.py +++ b/tests/test_litellm/proxy/proxy_server/test_proxy_config.py @@ -2198,6 +2198,34 @@ async def test_ProxyConfig_load_config_wires_general_settings_url_validation(tmp litellm.provider_url_destination_allowed_hosts = original_provider_hosts +@pytest.mark.asyncio +async def test_ssrf_block_message_names_a_config_section_load_config_honors(tmp_path, monkeypatch): + """Regression for LIT-8349: the remediation in the SSRF block message must point at a section that works.""" + from litellm.litellm_core_utils.url_utils import SSRFError, validate_url + + monkeypatch.setattr(litellm, "user_url_allowed_hosts", []) + monkeypatch.setattr(litellm, "user_url_validation", True) + with pytest.raises(SSRFError) as blocked: + validate_url("http://10.96.3.245:10002/agent.json") + section_match = re.search(r"add the host to `user_url_allowed_hosts` in (\w+)\.", str(blocked.value)) + assert section_match is not None, str(blocked.value) + section: Final = section_match.group(1) + assert section == "litellm_settings", f"block message points admins at {section}, which the docs contradict" + + f = tmp_path / "c.yaml" + f.write_text(f"model_list: []\n{section}:\n user_url_allowed_hosts:\n - '10.96.3.245:10002'\n") + monkeypatch.setattr("litellm.proxy.proxy_server.prisma_client", None) + monkeypatch.setattr("litellm.proxy.proxy_server.store_model_in_db", False) + monkeypatch.delenv("LITELLM_CONFIG_BUCKET_NAME", raising=False) + await ProxyConfig().load_config(router=None, config_file_path=str(f)) + + assert litellm.user_url_allowed_hosts == ["10.96.3.245:10002"], f"{section} did not apply the allowlist" + assert validate_url("http://10.96.3.245:10002/agent.json") == ( + "http://10.96.3.245:10002/agent.json", + "10.96.3.245:10002", + ) + + @pytest.mark.asyncio async def test_ProxyConfig_load_config_wires_config_reload_interval(tmp_path, monkeypatch): """general_settings.proxy_config_reload_interval_seconds must reach the proxy_server diff --git a/tests/test_litellm/proxy/test_native_compaction.py b/tests/test_litellm/proxy/test_native_compaction.py index d24624aacc5..9a6b4cdda65 100644 --- a/tests/test_litellm/proxy/test_native_compaction.py +++ b/tests/test_litellm/proxy/test_native_compaction.py @@ -7,6 +7,7 @@ import pytest from fastapi import FastAPI, Request from pydantic import TypeAdapter +import litellm from litellm.caching.caching import DualCache from litellm.exceptions import BadRequestError from litellm.litellm_core_utils.initialize_dynamic_callback_params import inherit_message_logging_privacy @@ -112,6 +113,7 @@ async def test_real_proxy_child_auth_privacy_and_body_policy( }))) return asyncio.sleep(0, result=ModelResponse(id="private-summary", model="compactor")) + monkeypatch.setattr(litellm, "max_budget", 0) monkeypatch.setattr(proxy_server.app, "dependency_overrides", {}) monkeypatch.setattr(proxy_server, "master_key", "sk-master-fixture") monkeypatch.setattr(proxy_server, "prisma_client", object()) From e30f9f578c9af0dd48b837a318a6246ad6e2f23e Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:05:33 -0700 Subject: [PATCH 02/11] fix(model_prices): registry audit 2026-09-22, absorb open pricing PRs (#42543) * fix(model_prices): registry audit 2026-09-22, absorb open pricing PRs Rolls the open registry-only PRs into one PR after re-verifying every value against the official provider source: OpenAI, Azure, Vertex AI and Gemini batch cache-read prices, Baseten model metadata from the authenticated inference API, Bedrock eu-west-2 Nemotron Super 3 pricing from the AWS offer file, and OpenRouter prices refreshed from the live OpenRouter models API Co-authored-by: sinksilk <785976238@qq.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): add groq/llama-guard-3-8b from the Groq model page Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): refresh openrouter deepseek aliases from live api and drop stale off-peak windows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): resolve baseten merge conflicts against main Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: sinksilk <785976238@qq.com> --- ...odel_prices_and_context_window_backup.json | 376 ++++++++++++++---- model_prices_and_context_window.json | 376 ++++++++++++++---- tests/test_litellm/test_cost_calculator.py | 24 ++ 3 files changed, 608 insertions(+), 168 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index b725094ae91..94786f250b0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4417,7 +4417,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -4456,7 +4457,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -4636,7 +4638,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, @@ -6094,7 +6097,8 @@ "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5.1-chat-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -6282,7 +6286,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6460,7 +6465,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", @@ -6533,7 +6539,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", @@ -6822,7 +6829,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 8.75e-08 }, "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, @@ -7287,7 +7295,11 @@ "output_cost_per_token_flex": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05 }, "azure/us/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7333,7 +7345,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/eu/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7379,7 +7395,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", @@ -7477,7 +7497,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { "cache_creation_input_token_cost": 6.25e-06, @@ -8900,7 +8922,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05 }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9003,7 +9029,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9106,7 +9136,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -9293,7 +9327,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 3.75e-08 }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", @@ -9390,7 +9425,8 @@ "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -10404,7 +10440,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -10443,7 +10480,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, @@ -10479,7 +10517,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -12908,6 +12947,23 @@ "supports_tool_choice": true, "output_cost_per_token": 1.86e-06 }, + "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.01e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, "litellm_provider": "bedrock", @@ -26782,7 +26838,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -26867,7 +26924,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 2.5e-08 }, "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -26946,7 +27004,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -27055,7 +27114,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -27112,7 +27172,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -27147,7 +27208,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -27880,7 +27942,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -27937,7 +28000,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -27995,7 +28059,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -28053,7 +28118,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -30385,7 +30451,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30442,7 +30509,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -30500,7 +30568,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -30558,7 +30627,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -35661,7 +35731,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -36087,7 +36158,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, @@ -36186,7 +36258,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -36809,6 +36882,15 @@ "supports_response_schema": false, "supports_tool_choice": true }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://console.groq.com/docs/model/llama-guard-3-8b" + }, "groq/gemma-7b-it": { "deprecation_date": "2024-12-18", "input_cost_per_token": 5e-08, @@ -43157,6 +43239,28 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "openrouter/bytedance/ui-tars-1.5-7b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, @@ -43328,21 +43432,21 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 9.31074e-07, + "input_cost_per_token": 8.92272e-07, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.862148e-06, + "output_cost_per_token": 1.784544e-06, "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.75895e-08, + "cache_read_input_token_cost": 7.4356e-08, "supports_audio_input": false, "supports_pdf_input": false, "supports_vision": false, @@ -52043,7 +52147,8 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_read_input_token_cost_batches": 1e-07 }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -52080,7 +52185,8 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_read_input_token_cost_batches": 2.5e-08 }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -52135,7 +52241,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -52245,7 +52352,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -52303,7 +52411,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -52319,7 +52428,8 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_read_input_token_cost_batches": 1e-07 }, "vertex_ai/imagegeneration@006": { "deprecation_date": "2025-09-24", @@ -69143,13 +69253,13 @@ "supports_web_search": false }, "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 262140, + "max_tokens": 262140, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -73178,16 +73288,16 @@ "supports_web_search": true }, "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, + "output_cost_per_token": 2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73222,15 +73332,14 @@ "supports_web_search": true }, "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9}, - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73243,15 +73352,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, + "cache_read_input_token_cost": 1.2726e-08, + "input_cost_per_token": 3.9996e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, + "output_cost_per_token": 1.19988e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73264,14 +73372,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 6.4e-07, + "output_cost_per_token": 8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73334,13 +73442,13 @@ }, "openrouter/~moonshotai/kimi-latest": { "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "input_cost_per_token": 1.4989e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.0758e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73378,19 +73486,19 @@ "supports_web_search": true }, "openrouter/~openai/gpt-luna-latest": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73496,14 +73604,14 @@ "supports_web_search": true }, "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -75959,6 +76067,106 @@ "supports_vision": true, "supports_web_search": true }, + "openrouter/openai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-luna-pro": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "openrouter/openai/o3-mini:batch": { "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 5.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index b725094ae91..94786f250b0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4417,7 +4417,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -4456,7 +4457,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -4636,7 +4638,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, @@ -6094,7 +6097,8 @@ "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5.1-chat-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -6282,7 +6286,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6460,7 +6465,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", @@ -6533,7 +6539,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", @@ -6822,7 +6829,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 8.75e-08 }, "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, @@ -7287,7 +7295,11 @@ "output_cost_per_token_flex": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05 }, "azure/us/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7333,7 +7345,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/eu/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7379,7 +7395,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", @@ -7477,7 +7497,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { "cache_creation_input_token_cost": 6.25e-06, @@ -8900,7 +8922,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05 }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9003,7 +9029,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9106,7 +9136,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -9293,7 +9327,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 3.75e-08 }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", @@ -9390,7 +9425,8 @@ "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -10404,7 +10440,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -10443,7 +10480,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, @@ -10479,7 +10517,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -12908,6 +12947,23 @@ "supports_tool_choice": true, "output_cost_per_token": 1.86e-06 }, + "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.01e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, "litellm_provider": "bedrock", @@ -26782,7 +26838,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -26867,7 +26924,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 2.5e-08 }, "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -26946,7 +27004,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -27055,7 +27114,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -27112,7 +27172,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -27147,7 +27208,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -27880,7 +27942,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -27937,7 +28000,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -27995,7 +28059,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -28053,7 +28118,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -30385,7 +30451,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30442,7 +30509,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -30500,7 +30568,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -30558,7 +30627,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -35661,7 +35731,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -36087,7 +36158,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, @@ -36186,7 +36258,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -36809,6 +36882,15 @@ "supports_response_schema": false, "supports_tool_choice": true }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://console.groq.com/docs/model/llama-guard-3-8b" + }, "groq/gemma-7b-it": { "deprecation_date": "2024-12-18", "input_cost_per_token": 5e-08, @@ -43157,6 +43239,28 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "openrouter/bytedance/ui-tars-1.5-7b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, @@ -43328,21 +43432,21 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 9.31074e-07, + "input_cost_per_token": 8.92272e-07, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.862148e-06, + "output_cost_per_token": 1.784544e-06, "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.75895e-08, + "cache_read_input_token_cost": 7.4356e-08, "supports_audio_input": false, "supports_pdf_input": false, "supports_vision": false, @@ -52043,7 +52147,8 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_read_input_token_cost_batches": 1e-07 }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -52080,7 +52185,8 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_read_input_token_cost_batches": 2.5e-08 }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -52135,7 +52241,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -52245,7 +52352,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -52303,7 +52411,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -52319,7 +52428,8 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_read_input_token_cost_batches": 1e-07 }, "vertex_ai/imagegeneration@006": { "deprecation_date": "2025-09-24", @@ -69143,13 +69253,13 @@ "supports_web_search": false }, "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 262140, + "max_tokens": 262140, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -73178,16 +73288,16 @@ "supports_web_search": true }, "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, + "output_cost_per_token": 2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73222,15 +73332,14 @@ "supports_web_search": true }, "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9}, - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73243,15 +73352,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, + "cache_read_input_token_cost": 1.2726e-08, + "input_cost_per_token": 3.9996e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, + "output_cost_per_token": 1.19988e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73264,14 +73372,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 6.4e-07, + "output_cost_per_token": 8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73334,13 +73442,13 @@ }, "openrouter/~moonshotai/kimi-latest": { "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "input_cost_per_token": 1.4989e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.0758e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73378,19 +73486,19 @@ "supports_web_search": true }, "openrouter/~openai/gpt-luna-latest": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73496,14 +73604,14 @@ "supports_web_search": true }, "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -75959,6 +76067,106 @@ "supports_vision": true, "supports_web_search": true }, + "openrouter/openai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-luna-pro": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "openrouter/openai/o3-mini:batch": { "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 5.5e-07, diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index 7d2a04c500f..ecc01857f8c 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -4847,3 +4847,27 @@ def test_cost_per_token_bedrock_qwen3_next_uses_regional_entry_not_us_rate( assert prompt_usd == pytest.approx(prompt_tokens * regional["input_cost_per_token"]) assert completion_usd == pytest.approx(completion_tokens * regional["output_cost_per_token"]) + + +def test_cost_per_token_bedrock_nemotron_super_3_uses_eu_west_2_entry_not_us_rate( + monkeypatch: pytest.MonkeyPatch, +) -> None: + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + + regional_key: Final = "bedrock/eu-west-2/nvidia.nemotron-super-3-120b" + regional: Final = litellm.model_cost[regional_key] + us: Final = litellm.model_cost["nvidia.nemotron-super-3-120b"] + assert regional["input_cost_per_token"] != us["input_cost_per_token"] + assert regional["output_cost_per_token"] != us["output_cost_per_token"] + + prompt_tokens, completion_tokens = 1000, 500 + prompt_usd, completion_usd = cost_per_token( + model=regional_key, + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + custom_llm_provider="bedrock", + ) + + assert prompt_usd == pytest.approx(prompt_tokens * regional["input_cost_per_token"]) + assert completion_usd == pytest.approx(completion_tokens * regional["output_cost_per_token"]) From bbc702cd8be9025c405e4789f37aa24ec45c7159 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:09:40 -0700 Subject: [PATCH 03/11] fix(gateway): expose /api/event_logging/batch on the gateway allowlist (#42572) * fix(gateway): expose /api/event_logging/batch on the gateway allowlist Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(gateway): route /api/event_logging to gateway pods in helm and terraform Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): stop max_budget leaking between proxy_server and native_compaction tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: kerry Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- gateway/routes/allowlist.py | 1 + helm/litellm/templates/ingress.yaml | 2 +- terraform/litellm/aws/locals.tf | 2 +- terraform/litellm/gcp/locals.tf | 2 +- tests/test_litellm/proxy/test_native_compaction.py | 1 + tests/test_litellm/proxy/test_proxy_server.py | 12 ++++++------ 6 files changed, 11 insertions(+), 9 deletions(-) diff --git a/gateway/routes/allowlist.py b/gateway/routes/allowlist.py index fe58e2dd58c..c4a3d3f7473 100644 --- a/gateway/routes/allowlist.py +++ b/gateway/routes/allowlist.py @@ -131,6 +131,7 @@ GATEWAY_EXACT_PATHS: frozenset[str] = frozenset( "/redoc", "/test", "/debug/memory/summary", + "/api/event_logging/batch", } ) diff --git a/helm/litellm/templates/ingress.yaml b/helm/litellm/templates/ingress.yaml index e6717821a57..e9f7ed4ec3f 100644 --- a/helm/litellm/templates/ingress.yaml +++ b/helm/litellm/templates/ingress.yaml @@ -61,7 +61,7 @@ "/v1/fine-tuning" "/fine-tuning" "/v1/responses" "/responses" "/v1/threads" "/threads" "/v1/assistants" "/assistants" "/v1/vector_stores" "/vector_stores" "/v1/indexes" "/v1/models" "/models" "/openai" "/engines" - "/v1/messages" "/messages" "/v1/skills" "/v1/a2a" "/a2a" + "/v1/messages" "/messages" "/v1/skills" "/v1/a2a" "/a2a" "/api/event_logging" "/v1/rerank" "/v2/rerank" "/rerank" "/v1/ocr" "/ocr" "/v1/rag" "/rag" "/v1/video" "/v1/videos" "/video" "/videos" "/v1/search" "/search" "/v1/containers" "/containers" "/v1/evals" "/v1/memory" "/queue/chat" diff --git a/terraform/litellm/aws/locals.tf b/terraform/litellm/aws/locals.tf index 778d31642c1..b89bd486d02 100644 --- a/terraform/litellm/aws/locals.tf +++ b/terraform/litellm/aws/locals.tf @@ -74,7 +74,7 @@ locals { "/v1/models*", "/models*", "/openai/*", "/engines/*", "/v1/messages*", "/messages*", - "/v1/skills/*", "/v1/a2a/*", + "/v1/skills/*", "/v1/a2a/*", "/api/event_logging*", "/v1/rerank*", "/v2/rerank*", "/rerank*", "/v1/ocr*", "/ocr*", "/v1/rag/*", "/rag/*", diff --git a/terraform/litellm/gcp/locals.tf b/terraform/litellm/gcp/locals.tf index d263c781449..e82892b27cb 100644 --- a/terraform/litellm/gcp/locals.tf +++ b/terraform/litellm/gcp/locals.tf @@ -43,7 +43,7 @@ locals { "/v1/models*", "/models*", "/openai/*", "/engines/*", "/v1/messages*", "/messages*", - "/v1/skills/*", "/v1/a2a/*", + "/v1/skills/*", "/v1/a2a/*", "/api/event_logging*", "/v1/rerank*", "/v2/rerank*", "/rerank*", "/v1/ocr*", "/ocr*", "/v1/rag/*", "/rag/*", diff --git a/tests/test_litellm/proxy/test_native_compaction.py b/tests/test_litellm/proxy/test_native_compaction.py index 9a6b4cdda65..778c1715530 100644 --- a/tests/test_litellm/proxy/test_native_compaction.py +++ b/tests/test_litellm/proxy/test_native_compaction.py @@ -116,6 +116,7 @@ async def test_real_proxy_child_auth_privacy_and_body_policy( monkeypatch.setattr(litellm, "max_budget", 0) monkeypatch.setattr(proxy_server.app, "dependency_overrides", {}) monkeypatch.setattr(proxy_server, "master_key", "sk-master-fixture") + monkeypatch.setattr(litellm, "max_budget", 0.0) monkeypatch.setattr(proxy_server, "prisma_client", object()) monkeypatch.setattr(proxy_server, "user_api_key_cache", cache) monkeypatch.setattr(proxy_server, "llm_router", None) diff --git a/tests/test_litellm/proxy/test_proxy_server.py b/tests/test_litellm/proxy/test_proxy_server.py index 26bfd5c52bd..32b89885ac2 100644 --- a/tests/test_litellm/proxy/test_proxy_server.py +++ b/tests/test_litellm/proxy/test_proxy_server.py @@ -3200,7 +3200,7 @@ def test_normalize_datetime_for_sorting(): @pytest.mark.asyncio -async def test_add_proxy_budget_to_db_only_creates_user_no_keys(): +async def test_add_proxy_budget_to_db_only_creates_user_no_keys(monkeypatch: pytest.MonkeyPatch): """ Test that _add_proxy_budget_to_db only creates a user and no keys are added. @@ -3218,8 +3218,8 @@ async def test_add_proxy_budget_to_db_only_creates_user_no_keys(): from litellm.proxy.proxy_server import ProxyStartupEvent # Set up required litellm settings - litellm.budget_duration = "30d" - litellm.max_budget = 100.0 + monkeypatch.setattr(litellm, "budget_duration", "30d") + monkeypatch.setattr(litellm, "max_budget", 100.0) litellm_proxy_budget_name = "litellm-proxy-budget" @@ -3258,7 +3258,7 @@ async def test_add_proxy_budget_to_db_only_creates_user_no_keys(): @pytest.mark.asyncio -async def test_add_proxy_budget_to_db_backfills_budget_reset_at(): +async def test_add_proxy_budget_to_db_backfills_budget_reset_at(monkeypatch: pytest.MonkeyPatch): """ Test that _upsert_proxy_budget_with_reset_at_backfill issues a conditional update_many with `WHERE budget_reset_at IS NULL` to backfill the column on @@ -3276,8 +3276,8 @@ async def test_add_proxy_budget_to_db_backfills_budget_reset_at(): import litellm from litellm.proxy.proxy_server import ProxyStartupEvent - litellm.budget_duration = "30d" - litellm.max_budget = 100.0 + monkeypatch.setattr(litellm, "budget_duration", "30d") + monkeypatch.setattr(litellm, "max_budget", 100.0) litellm_proxy_budget_name = "litellm-proxy-budget" mock_prisma = MagicMock() From 12dffbafd6dce04a0ea81c93b35ff83f871027d6 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 16:10:49 -0500 Subject: [PATCH 04/11] fix(proxy): honor DATABASE_DISABLE_PREPARED_STATEMENTS in the litellm CLI (#42556) * fix(proxy): honor DATABASE_DISABLE_PREPARED_STATEMENTS in the litellm CLI Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): pooled pgbouncer url keeps a single pgbouncer=true when the upstream already carries it Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): reject a malformed DATABASE_DISABLE_PREPARED_STATEMENTS even when the config already enables it Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: yassin Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/proxy_cli.py | 7 +- tests/test_litellm/proxy/db/test_pgbouncer.py | 7 + tests/test_litellm/proxy/test_proxy_cli.py | 166 ++++++++++++++++++ 3 files changed, 179 insertions(+), 1 deletion(-) diff --git a/litellm/proxy/proxy_cli.py b/litellm/proxy/proxy_cli.py index 78885461724..40140974198 100644 --- a/litellm/proxy/proxy_cli.py +++ b/litellm/proxy/proxy_cli.py @@ -1283,6 +1283,7 @@ def run_server( if os.getenv("DATABASE_URL", None) is not None or os.getenv("DIRECT_URL", None) is not None: from litellm.proxy.db.db_url_settings import ( + DISABLE_PREPARED_STATEMENTS_ENV_VAR, add_missing_query_params, idle_lifetime_params, reader_shareable_params, @@ -1305,12 +1306,16 @@ def run_server( sys.exit(1) from litellm.secret_managers.main import get_secret + env_disable_prepared_statements: Final = token_auth_flag_enabled( + os.getenv(DISABLE_PREPARED_STATEMENTS_ENV_VAR), env_var=DISABLE_PREPARED_STATEMENTS_ENV_VAR + ) + disable_prepared_statements: Final = db_disable_prepared_statements or env_disable_prepared_statements connection_url_params: Final = _build_db_connection_url_params( connection_limit=db_connection_pool_limit, pool_timeout=db_connection_timeout, connect_timeout=db_connect_timeout, socket_timeout=db_socket_timeout, - disable_prepared_statements=db_disable_prepared_statements, + disable_prepared_statements=disable_prepared_statements, extra_params=db_extra_connection_params, ) lifetime_params: Final = idle_lifetime_params(general_settings.get("database_max_idle_connection_lifetime")) diff --git a/tests/test_litellm/proxy/db/test_pgbouncer.py b/tests/test_litellm/proxy/db/test_pgbouncer.py index bf7df3077ea..c69c8d015a3 100644 --- a/tests/test_litellm/proxy/db/test_pgbouncer.py +++ b/tests/test_litellm/proxy/db/test_pgbouncer.py @@ -122,6 +122,13 @@ class TestPlanPgBouncer: "pgbouncer": "true", } + def test_an_upstream_that_already_disables_prepared_statements_gets_a_single_pgbouncer_flag(self): + pooled: Final = _plan("postgresql://app:pw@db/litellm?connection_limit=5&pgbouncer=true").pooled_url + assert urllib.parse.parse_qsl(urllib.parse.urlsplit(pooled).query) == [ + ("connection_limit", "5"), + ("pgbouncer", "true"), + ] + @pytest.mark.parametrize("hop_param", ["channel_binding=require", "gssencmode=require"]) def test_transport_params_for_the_postgres_hop_stay_off_the_plain_tcp_loopback_url(self, hop_param: str): pooled: Final = _plan(f"postgresql://app:pw@db/litellm?connection_limit=5&{hop_param}").pooled_url diff --git a/tests/test_litellm/proxy/test_proxy_cli.py b/tests/test_litellm/proxy/test_proxy_cli.py index a38470d1fdf..d2d71d6df05 100644 --- a/tests/test_litellm/proxy/test_proxy_cli.py +++ b/tests/test_litellm/proxy/test_proxy_cli.py @@ -1174,6 +1174,172 @@ class TestProxyInitializationHelpers: else: assert "pgbouncer" not in appended_params + @pytest.mark.parametrize( + "env_value, config_value, expect_pgbouncer", + [ + ("true", None, True), + ("1", None, True), + ("false", None, False), + (None, None, False), + ("true", False, True), + ("false", True, True), + ], + ) + @patch("subprocess.run") + @patch("atexit.register") + @patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database") + @patch( + "litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False + ) + def test_disable_prepared_statements_env_var_forwarded_to_url( + self, + mock_should_update, + mock_setup_db, + mock_atexit_register, + mock_subprocess_run, + env_value, + config_value, + expect_pgbouncer, + ): + from click.testing import CliRunner + + from litellm.proxy.proxy_cli import run_server + + runner = CliRunner() + mock_subprocess_run.return_value = MagicMock(returncode=0) + + general_settings = {"database_url": "postgresql://test:test@localhost:5432/test"} + if config_value is not None: + general_settings["database_disable_prepared_statements"] = config_value + mock_proxy_module = MagicMock( + app=MagicMock(), + ProxyConfig=MagicMock(), + KeyManagementSettings=MagicMock(), + save_worker_config=MagicMock(), + ) + mock_proxy_module.ProxyConfig.return_value.get_config = AsyncMock( + return_value={"general_settings": general_settings} + ) + + clean_env = { + k: v + for k, v in os.environ.items() + if k not in ("DATABASE_URL", "DIRECT_URL", "DATABASE_DISABLE_PREPARED_STATEMENTS") + } + if env_value is not None: + clean_env["DATABASE_DISABLE_PREPARED_STATEMENTS"] = env_value + + with ( + patch.dict(os.environ, clean_env, clear=True), + patch.dict( + "sys.modules", + { + "proxy_server": mock_proxy_module, + "litellm.proxy.proxy_server": mock_proxy_module, + }, + ), + patch( + "litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args" + ) as mock_get_args, + patch( + "litellm.proxy.proxy_cli.append_query_params", + side_effect=lambda url, params: str(url), + ) as mock_append_query_params, + ): + mock_get_args.return_value = { + "app": "litellm.proxy.proxy_server:app", + "host": "localhost", + "port": 8000, + } + + result = runner.invoke( + run_server, + ["--local", "--config", "test-config.yaml", "--skip_server_startup"], + ) + + assert ( + result.exit_code == 0 + ), f"exit_code={result.exit_code}, output={result.output}" + appended_params = mock_append_query_params.call_args.args[1] + if expect_pgbouncer: + assert appended_params["pgbouncer"] == "true", appended_params + else: + assert "pgbouncer" not in appended_params, appended_params + + @patch("subprocess.run") + @patch("atexit.register") + @patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database") + @patch( + "litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False + ) + def test_malformed_disable_prepared_statements_env_var_is_rejected_even_when_config_enables_it( + self, + mock_should_update, + mock_setup_db, + mock_atexit_register, + mock_subprocess_run, + ): + from click.testing import CliRunner + + from litellm.proxy.proxy_cli import run_server + + runner = CliRunner() + mock_subprocess_run.return_value = MagicMock(returncode=0) + + mock_proxy_module = MagicMock( + app=MagicMock(), + ProxyConfig=MagicMock(), + KeyManagementSettings=MagicMock(), + save_worker_config=MagicMock(), + ) + mock_proxy_module.ProxyConfig.return_value.get_config = AsyncMock( + return_value={ + "general_settings": { + "database_url": "postgresql://test:test@localhost:5432/test", + "database_disable_prepared_statements": True, + } + } + ) + + clean_env = { + k: v + for k, v in os.environ.items() + if k not in ("DATABASE_URL", "DIRECT_URL", "DATABASE_DISABLE_PREPARED_STATEMENTS") + } + clean_env["DATABASE_DISABLE_PREPARED_STATEMENTS"] = "enabled" + + with ( + patch.dict(os.environ, clean_env, clear=True), + patch.dict( + "sys.modules", + { + "proxy_server": mock_proxy_module, + "litellm.proxy.proxy_server": mock_proxy_module, + }, + ), + patch( + "litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args" + ) as mock_get_args, + patch( + "litellm.proxy.proxy_cli.append_query_params", + side_effect=lambda url, params: str(url), + ) as mock_append_query_params, + ): + mock_get_args.return_value = { + "app": "litellm.proxy.proxy_server:app", + "host": "localhost", + "port": 8000, + } + + result = runner.invoke( + run_server, + ["--local", "--config", "test-config.yaml", "--skip_server_startup"], + ) + + assert isinstance(result.exception, ValueError), f"exit_code={result.exit_code}, output={result.output}" + assert "DATABASE_DISABLE_PREPARED_STATEMENTS" in str(result.exception), result.exception + mock_append_query_params.assert_not_called() + @patch("uvicorn.run") @patch("atexit.register") @patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database") From cd69342eef5a317c8f54d39bfaddf06884f3e0c5 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:11:31 -0700 Subject: [PATCH 05/11] chore(prices): sync Vertex AI prices: 20 models (#42577) deep-research-pro-preview-12-2025: cache_read_input_token_cost_batches vertex_ai/deep-research-pro-preview-12-2025: cache_read_input_token_cost_batches gemini-3-pro-image: cache_read_input_token_cost_batches vertex_ai/gemini-3-pro-image: cache_read_input_token_cost_batches gemini-3.1-flash-image: cache_read_input_token_cost_batches vertex_ai/gemini-3.1-flash-image: cache_read_input_token_cost_batches gemini-3.1-flash-lite: cache_read_input_token_cost_batches vertex_ai/gemini-3.1-flash-lite: cache_read_input_token_cost_batches gemini-3.1-flash-lite-image: cache_read_input_token_cost_batches vertex_ai/gemini-3.1-flash-lite-image: cache_read_input_token_cost_batches gemini-3.5-flash: cache_read_input_token_cost_batches vertex_ai/gemini-3.5-flash: cache_read_input_token_cost_batches gemini-3.5-flash-lite: cache_read_input_token_cost_batches vertex_ai/gemini-3.5-flash-lite: cache_read_input_token_cost_batches gemini-3.6-flash: cache_read_input_token_cost_batches vertex_ai/gemini-3.6-flash: cache_read_input_token_cost_batches gemini-3.7-flash: cache_read_input_token_cost_batches vertex_ai/gemini-3.7-flash: cache_read_input_token_cost_batches gemini-3.8-flash: cache_read_input_token_cost_batches vertex_ai/gemini-3.8-flash: cache_read_input_token_cost_batches Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 20 +++++++++++++++++++ model_prices_and_context_window.json | 20 +++++++++++++++++++ 2 files changed, 40 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 94786f250b0..431e965524e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -26790,6 +26790,7 @@ "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "deprecation_date": "2027-05-28", @@ -26883,6 +26884,7 @@ }, "gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, @@ -26967,6 +26969,7 @@ }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, @@ -27060,6 +27063,7 @@ "cache_read_input_audio_token_cost": 5e-08, "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_audio_token": 5e-07, @@ -27120,6 +27124,7 @@ "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_token": 3e-07, @@ -27177,6 +27182,7 @@ }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -27888,6 +27894,7 @@ "prompt_cache_min_tokens": 4096, "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_token": 1.5e-06, "input_cost_per_audio_token": 1.5e-06, "litellm_provider": "vertex_ai", @@ -27948,6 +27955,7 @@ "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -28006,6 +28014,7 @@ "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -28065,6 +28074,7 @@ "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -30397,6 +30407,7 @@ "prompt_cache_min_tokens": 4096, "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai-language-models", @@ -30457,6 +30468,7 @@ "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -30515,6 +30527,7 @@ "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -30574,6 +30587,7 @@ "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -52123,6 +52137,7 @@ "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "deprecation_date": "2027-05-28", @@ -52168,6 +52183,7 @@ }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, @@ -52204,6 +52220,7 @@ }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, @@ -52297,6 +52314,7 @@ "cache_read_input_audio_token_cost": 5e-08, "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_audio_token": 5e-07, @@ -52358,6 +52376,7 @@ "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_token": 3e-07, @@ -52416,6 +52435,7 @@ }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 94786f250b0..431e965524e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26790,6 +26790,7 @@ "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "deprecation_date": "2027-05-28", @@ -26883,6 +26884,7 @@ }, "gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, @@ -26967,6 +26969,7 @@ }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, @@ -27060,6 +27063,7 @@ "cache_read_input_audio_token_cost": 5e-08, "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_audio_token": 5e-07, @@ -27120,6 +27124,7 @@ "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_token": 3e-07, @@ -27177,6 +27182,7 @@ }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -27888,6 +27894,7 @@ "prompt_cache_min_tokens": 4096, "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_token": 1.5e-06, "input_cost_per_audio_token": 1.5e-06, "litellm_provider": "vertex_ai", @@ -27948,6 +27955,7 @@ "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -28006,6 +28014,7 @@ "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -28065,6 +28074,7 @@ "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -30397,6 +30407,7 @@ "prompt_cache_min_tokens": 4096, "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai-language-models", @@ -30457,6 +30468,7 @@ "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -30515,6 +30527,7 @@ "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -30574,6 +30587,7 @@ "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, @@ -52123,6 +52137,7 @@ "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "deprecation_date": "2027-05-28", @@ -52168,6 +52183,7 @@ }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, @@ -52204,6 +52220,7 @@ }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, @@ -52297,6 +52314,7 @@ "cache_read_input_audio_token_cost": 5e-08, "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_audio_token": 5e-07, @@ -52358,6 +52376,7 @@ "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_token": 3e-07, @@ -52416,6 +52435,7 @@ }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, From 989d7b87b2d30982a6300dde227ec45d8f60f4ce Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:14:13 -0700 Subject: [PATCH 06/11] fix(proxy): attribute provider and model_info on pre_call_hook rejections (#41077) * fix(proxy): attribute provider and model info on pre-call rejected requests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): keep pre-call rejections out of deployment cooldown and prometheus deployment state Stamp model_info only into the logging metadata so the router's failure callbacks do not count a key-level 429 or guardrail 403 against the deployment, treat a resolved plus an unresolved deployment as ambiguous provider attribution, and stop the prometheus deployment counters and deployment_state from treating a proxy-side reject as a selected deployment Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): skip deployment attribution when the rejected body's model is not a string Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(prometheus): bucket non-string request models as other instead of raising in failure hook Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): resolve team deployments and treat guardrail rejects as proxy-side in failure attribution Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(prometheus): flag pre-routing rejects instead of matching exception names Post-call GuardrailRaisedException failures kept their deployment labels on main but lost them on this branch because every GuardrailRaisedException was treated as a pre-routing reject. The proxy failure path now flags litellm_params with proxy_rejected_before_routing only when it adds deployment attribution itself, and the Prometheus logger keys deployment selection off that flag Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): key pre-routing reject flag off provider handoff, not caller metadata Caller-supplied metadata.model_info (kept for keys allowed to override pricing) no longer suppresses proxy_rejected_before_routing. The hook now checks the logging object's first_api_call_start_time, which only the provider handoff sets, so Prometheus never records a deployment failure for a request that was rejected before routing. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(e2e): poll for both served and rejected spend rows before asserting attribution Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: yucheng --- litellm/constants.py | 3 + litellm/integrations/prometheus.py | 19 +- litellm/proxy/utils.py | 101 ++++ tests/e2e/AGENTS.md | 2 +- .../coverage_registry/quota_management.yaml | 1 + tests/e2e/models.py | 1 + .../spend_tracking/test_spend_tracking_e2e.py | 46 +- ...ometheus_deployment_state_proxy_rejects.py | 101 ++++ ..._prometheus_requested_model_cardinality.py | 16 + .../test_post_call_failure_hook.py | 456 +++++++++++++++++- 10 files changed, 734 insertions(+), 12 deletions(-) create mode 100644 tests/test_litellm/integrations/test_prometheus_deployment_state_proxy_rejects.py diff --git a/litellm/constants.py b/litellm/constants.py index 1012ca831f2..e5b662bd515 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -238,6 +238,9 @@ LOGS_GUARDRAIL_INFORMATION_MARKER: Final = "_litellm_logs_guardrail_information" # llm_provider stamped on proxy-side rate limit errors when the model resolves to no deployment PROXY_LLM_PROVIDER_FALLBACK: Final = "litellm_proxy" +# litellm_params flag on failure logs for requests the proxy rejected before routing to a deployment +PROXY_REJECTED_BEFORE_ROUTING_KEY: Final = "proxy_rejected_before_routing" + # Generic fallback for unknown models DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET: Final = int( os.getenv("DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET", 128) diff --git a/litellm/integrations/prometheus.py b/litellm/integrations/prometheus.py index 28ac9f5cdae..d62a6c3427a 100644 --- a/litellm/integrations/prometheus.py +++ b/litellm/integrations/prometheus.py @@ -18,7 +18,7 @@ from typing_extensions import ReadOnly, TypedDict import litellm from litellm._logging import print_verbose, verbose_logger -from litellm.constants import PROXY_LLM_PROVIDER_FALLBACK +from litellm.constants import PROXY_LLM_PROVIDER_FALLBACK, PROXY_REJECTED_BEFORE_ROUTING_KEY from litellm.exceptions import ( validate_rate_limit_category, validate_rate_limit_type, @@ -214,17 +214,22 @@ def _get_proxy_llm_router() -> Router | None: return llm_router -def _bounded_requested_model_label(requested_model: str | None, router_originated: bool = False) -> str | None: +def _bounded_requested_model_label(requested_model: object, router_originated: bool = False) -> str | None: """ Bound ``requested_model`` label cardinality: names the router recognizes (model names, deployment ids, aliases, routing groups, team public model names) or matches via a global or team wildcard/pattern route keep their own label value; any other client-supplied string collapses into the - single ``other`` bucket. With no proxy router to vouch for the string, - client-supplied values collapse to ``other`` while ``router_originated`` - values (emitted by an SDK ``Router``'s own deployment failure and - fallback events, where the proxy router never exists) pass through. + single ``other`` bucket, as does any non-string request ``model`` value. + With no proxy router to vouch for the string, client-supplied values + collapse to ``other`` while ``router_originated`` values (emitted by an + SDK ``Router``'s own deployment failure and fallback events, where the + proxy router never exists) pass through. """ + if requested_model is None: + return None + if not isinstance(requested_model, str): + return UNRECOGNIZED_REQUESTED_MODEL_LABEL if not requested_model: return requested_model llm_router: Final = _get_proxy_llm_router() @@ -2832,7 +2837,7 @@ class PrometheusLogger(CustomLogger): # On LiteLLM-side rejects (no deployment picked), route request_kwargs["model"] # into requested_model and leave deployment-scoped labels empty. - deployment_selected: Final = bool(model_id) + deployment_selected: Final = bool(model_id) and not _litellm_params.get(PROXY_REJECTED_BEFORE_ROUTING_KEY) if deployment_selected: label_litellm_model_name = litellm_model_name label_model_id = model_id diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index ea3ecb7f637..c7ce9d081d6 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -52,6 +52,7 @@ from litellm.constants import ( DEFAULT_MODEL_CREATED_AT_TIME, LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL, MAX_TEAM_LIST_LIMIT, + PROXY_REJECTED_BEFORE_ROUTING_KEY, REDIS_SPEND_LOGS_BUFFER_DEQUEUE_COUNT, SPEND_LOG_QUEUE_MAX_BYTES, SPEND_LOG_WRITE_BATCH_MAX_BYTES, @@ -979,6 +980,92 @@ def _failure_usage_to_lift( _EMPTY_LIFT: Final = MappingProxyType({}) +def _stamp_deployment_attribution( + litellm_params: dict[str, object], model_group: str | None, team_id: str | None, dispatched: bool +) -> Mapping[str, object]: + """Stamp provider and logging-metadata attribution onto ``litellm_params`` and return it. + ``litellm_params["model_info"]`` stays unset: the router's cooldown and per-deployment rpm + callbacks key off it and must not count a proxy-side reject against the deployment. A failure + after the provider handoff keeps the metadata the router stamped; a request that never reached a + provider is flagged ``PROXY_REJECTED_BEFORE_ROUTING_KEY`` (deployment metrics key off it) whatever + its metadata says, since ``metadata.model_info`` can be caller supplied.""" + attribution: Final = _deployment_attribution_for_model_group(model_group, team_id) + if "custom_llm_provider" in attribution: + litellm_params["custom_llm_provider"] = attribution["custom_llm_provider"] + if dispatched: + return attribution + litellm_params[PROXY_REJECTED_BEFORE_ROUTING_KEY] = True + if "model_info" not in attribution: + return attribution + if litellm_params.get("metadata") is None: + litellm_params["metadata"] = {} # mutable-ok: legacy logging payload is populated in place + metadata: Final = litellm_params["metadata"] + if not isinstance(metadata, dict): + return attribution + metadata.setdefault("model_info", attribution["model_info"]) + metadata.setdefault("deployment", attribution["deployment"]) + return attribution + + +def _deployment_attribution_for_model_group(model_group: object, team_id: str | None) -> Mapping[str, object]: + """Provider fields the router would have stamped had it reached a deployment: + ``custom_llm_provider`` when every deployment in the group resolves to the same + provider, plus ``model_info`` and ``deployment`` when the group has exactly one. + ``team_id`` picks the key's team deployments over a global group of the same public name.""" + if not isinstance(model_group, str): + return _EMPTY_LIFT + + from litellm.proxy.proxy_server import llm_router + + if llm_router is None: + return _EMPTY_LIFT + deployments: Final = llm_router.get_model_list(model_name=model_group, team_id=team_id) + if not deployments: + return _EMPTY_LIFT + + def _provider_for_deployment(deployment: Mapping[str, object]) -> str | None: + litellm_params: Final = cast( # cast-ok: router deployment parameters are mapping-shaped + Mapping[str, object], deployment["litellm_params"] + ) + try: + provider: Final = litellm.get_llm_provider( + model=cast(str, litellm_params["model"]), # cast-ok: router deployment model is a string + custom_llm_provider=cast( # cast-ok: router deployment provider is optional + str | None, litellm_params.get("custom_llm_provider") + ), + )[1] + return cast(str | None, provider) # cast-ok: provider resolver returns an optional provider string + except Exception: # noqa: BLE001 # get_llm_provider raises for unmapped models + return None + + providers: Final = frozenset(_provider_for_deployment(deployment) for deployment in deployments) + shared_provider: Final = next(iter(providers)) if len(providers) == 1 else None + single_deployment: Final = deployments[0] if len(deployments) == 1 else None + single_deployment_params: Final = ( + cast( # cast-ok: router deployment parameters are mapping-shaped + Mapping[str, object], single_deployment["litellm_params"] + ) + if single_deployment is not None + else None + ) + return MappingProxyType( + { + # mutable-ok: frozen immediately by the outer MappingProxyType + **({"custom_llm_provider": shared_provider} if shared_provider is not None else {}), + **( + { # mutable-ok: frozen immediately by the outer MappingProxyType + "model_info": dict( # mutable-ok: preserve the router's mutable model-info payload + single_deployment.get("model_info") or {} + ), + "deployment": single_deployment_params["model"], + } + if single_deployment is not None and single_deployment_params is not None + else {} # mutable-ok: frozen immediately by the outer MappingProxyType + ), + } + ) + + def _call_type_for_route(route: str | None) -> str | None: """The route's call type when it maps to a single operation (its async and sync variants); None for routes shared by several operations, since the method is not known here.""" @@ -3227,11 +3314,25 @@ class ProxyLogging: elif k not in ("model", "user", "litellm_logging_obj"): _optional_params[k] = v + attribution: Final = _stamp_deployment_attribution( + _litellm_params, + request_data.get("model"), + user_api_key_dict.team_id, + dispatched=litellm_logging_obj.model_call_details.get("first_api_call_start_time") is not None, + ) + litellm_logging_obj.update_environment_variables( model=request_data.get("model", ""), user=request_data.get("user", ""), optional_params=_optional_params, litellm_params=_litellm_params, + **( + { # mutable-ok: frozen immediately by keyword expansion + "custom_llm_provider": attribution["custom_llm_provider"] + } + if "custom_llm_provider" in attribution + else {} # mutable-ok: frozen immediately by keyword expansion + ), ) input: list | str | dict = "" diff --git a/tests/e2e/AGENTS.md b/tests/e2e/AGENTS.md index 6ea75b806d0..ad1e0322787 100644 --- a/tests/e2e/AGENTS.md +++ b/tests/e2e/AGENTS.md @@ -216,7 +216,7 @@ quota_management... | isolates_per_model | isolates_per_member | isolates_per_group | enforced_across_keys | routes_to_fallback | reseed_matches_db | reports_spend | logs_cost | zero_cost | matches_sum_of_logs | loses_no_spend | attributes_spend | writes_own_rows - | writes_failure_row | returns_cost | keeps_total | joins_key | reports_alias_and_email + | writes_failure_row | attributes_provider | returns_cost | keeps_total | joins_key | reports_alias_and_email | health_rows_keep_service_account | retrieve_batch_cost_joins_retrieving_key | poller_batch_cost_joins_creating_key | bills_under_request_session e.g. quota_management.ratelimit.rpm.blocks_over_limit exercised_on=[chat_completions, messages] diff --git a/tests/e2e/coverage_registry/quota_management.yaml b/tests/e2e/coverage_registry/quota_management.yaml index 5432c5095a2..5ea48fdcd9d 100644 --- a/tests/e2e/coverage_registry/quota_management.yaml +++ b/tests/e2e/coverage_registry/quota_management.yaml @@ -51,6 +51,7 @@ - {id: quota_management.spend_tracking.end_user.attributes_spend, module: quota_management, tier: P1, behavior: spend_tracking, variant: end_user, assertions: [attributes_spend], exercised_on: [chat_completions], source: "proxy/spend_tracking/spend_tracking_utils.py", rationale: "user= attribution lands the end-user id on the spend row"} - {id: quota_management.spend_tracking.per_model.writes_own_rows, module: quota_management, tier: P2, behavior: spend_tracking, variant: per_model, assertions: [writes_own_rows], exercised_on: [chat_completions], source: "proxy/spend_tracking/spend_tracking_utils.py", rationale: "Each model on a shared key gets its own spend row"} - {id: quota_management.spend_tracking.failure.writes_failure_row, module: quota_management, tier: P1, behavior: spend_tracking, variant: failure, assertions: [writes_failure_row], exercised_on: [chat_completions], source: "proxy/spend_tracking/spend_log_error_logger.py", rationale: "A failed call writes a failure-status spend row"} +- {id: quota_management.spend_tracking.failure.attributes_provider, module: quota_management, tier: P1, behavior: spend_tracking, variant: failure, assertions: [attributes_provider], exercised_on: [chat_completions], source: "proxy/utils.py", rationale: "A request rejected in pre_call_hook (rate limit, guardrail) still lands its single deployment's provider and model_id on the failure spend row"} - {id: quota_management.spend_tracking.spend_calculate.returns_cost, module: quota_management, tier: P2, behavior: spend_tracking, variant: spend_calculate, assertions: [returns_cost], exercised_on: [spend_calculate], source: "proxy/spend_tracking/spend_management_endpoints.py", rationale: "/spend/calculate prices a hypothetical request at nonzero cost"} - {id: quota_management.spend_tracking.pagination.keeps_total, module: quota_management, tier: P2, behavior: spend_tracking, variant: pagination, assertions: [keeps_total], exercised_on: [chat_completions], source: "proxy/spend_tracking/spend_management_endpoints.py", rationale: "Spend-logs v2 pagination caps page size without losing the total"} - {id: quota_management.spend_tracking.cache_write.bills_cache_creation_rate, module: quota_management, tier: P1, behavior: spend_tracking, variant: cache_write, assertions: [bills_cache_creation_rate], exercised_on: [chat_completions], source: "litellm_core_utils/llm_cost_calc/utils.py", rationale: "OpenAI cache-write tokens land on the spend row as cache-creation tokens billed at the cache-creation rate, not silently at the input rate (#34046)"} diff --git a/tests/e2e/models.py b/tests/e2e/models.py index 74cad3ad8df..bc81d1015ba 100644 --- a/tests/e2e/models.py +++ b/tests/e2e/models.py @@ -952,6 +952,7 @@ class SpendLogRow(BaseModel): cache_hit: str | None = None call_type: str | None = None custom_llm_provider: str | None = None + model_id: str | None = None team_id: str | None = None user: str | None = None end_user: str | None = None diff --git a/tests/e2e/quota_management/spend_tracking/test_spend_tracking_e2e.py b/tests/e2e/quota_management/spend_tracking/test_spend_tracking_e2e.py index 8a91e53e7d7..6ca6f8cee55 100644 --- a/tests/e2e/quota_management/spend_tracking/test_spend_tracking_e2e.py +++ b/tests/e2e/quota_management/spend_tracking/test_spend_tracking_e2e.py @@ -21,9 +21,9 @@ from math import isclose from typing import Final import pytest -from e2e_http import Success +from e2e_http import RateLimitedError, Success from lifecycle import ResourceManager -from models import LiteLLMParamsBody, SpendLogs, SpendLogsParams +from models import KeyGenerateBody, LiteLLMParamsBody, SpendLogs, SpendLogsParams from spend_e2e_client import SpendClient, SpendLogRow, is_ok, unique_marker, unwrap pytestmark = pytest.mark.e2e @@ -43,6 +43,7 @@ def _summarize(rows: list[SpendLogRow]) -> list[dict[str, object]]: "cache_hit", "call_type", "custom_llm_provider", + "model_id", "prompt_tokens", "completion_tokens", "total_tokens", @@ -498,6 +499,47 @@ def test_failure_call_writes_failure_status_row( assert (failure_row.spend or 0) == 0.0, "failed call must not be charged" +@pytest.mark.covers("quota_management.spend_tracking.failure.attributes_provider") +def test_pre_call_rejection_row_attributes_provider_and_model_id( + client: SpendClient, resources: ResourceManager +) -> None: + """A request the proxy rejects before the router picks a deployment (here the + key's rpm limit, a pre_call_hook 429) never reaches the code that stamps the + deployment onto the log. The failure row must still carry the provider and + model_id of the model group's only deployment, so per-provider failure reports + can count it.""" + model = f"e2e-spend-precall-{unique_marker()}" + model_id = client.proxy.create_model( + model, LiteLLMParamsBody(model="openai/gpt-5.5", api_key="os.environ/OPENAI_API_KEY") + ) + resources.defer(lambda: client.proxy.delete_model(model_id)) + key = client.proxy.generate_key(KeyGenerateBody(models=[model], rpm_limit=1)) + resources.defer(lambda: client.proxy.delete_key(key)) + + unwrap(client.chat(key, model, f"reply with one word {unique_marker()}", max_tokens=8)) + rejected = client.chat(key, model, f"over the rpm limit {unique_marker()}", max_tokens=8) + assert isinstance(rejected, RateLimitedError), ( + f"the second call on an rpm_limit=1 key must be rejected with 429 before routing, got {rejected}" + ) + + rows = client.poll_logs_for_key( + key, + min_rows=2, + predicate=lambda rs: {r.status for r in rs} >= {"success", "failure"}, + ) + success_row = _require_row(rows, lambda r: r.status == "success", "for the served call") + failure_row = _require_row(rows, lambda r: r.status == "failure", "for the rate-limited call") + + assert failure_row.custom_llm_provider == success_row.custom_llm_provider, ( + f"rejected call lost its provider: failure row {failure_row.custom_llm_provider!r} vs " + f"served row {success_row.custom_llm_provider!r}; {_summarize(rows)}" + ) + assert failure_row.model_id == model_id, ( + f"rejected call lost its deployment: failure row model_id {failure_row.model_id!r} vs " + f"registered {model_id!r}; {_summarize(rows)}" + ) + + @pytest.mark.covers("quota_management.spend_tracking.spend_calculate.returns_cost") def test_spend_calculate_returns_nonzero_cost(client: SpendClient) -> None: cost = client.calculate_spend( diff --git a/tests/test_litellm/integrations/test_prometheus_deployment_state_proxy_rejects.py b/tests/test_litellm/integrations/test_prometheus_deployment_state_proxy_rejects.py new file mode 100644 index 00000000000..fedfc2b0848 --- /dev/null +++ b/tests/test_litellm/integrations/test_prometheus_deployment_state_proxy_rejects.py @@ -0,0 +1,101 @@ +""" +LIT-7701 attributes a pre_call_hook rejection's failure log to the model +group's single deployment (``model_id`` and ``custom_llm_provider``) and flags +it with ``PROXY_REJECTED_BEFORE_ROUTING_KEY``. The deployment health metrics +must keep treating such rejects as "no deployment picked": a key rate limit or +guardrail block never reached the deployment, so it must not flip +``litellm_deployment_state`` to partial outage or count as a deployment failure +response. A failure raised after the router picked a deployment (a post-call +guardrail block, a provider error) carries no flag and keeps its deployment labels. +""" + +import pytest +from fastapi import HTTPException +from prometheus_client import REGISTRY + +from litellm.constants import PROXY_REJECTED_BEFORE_ROUTING_KEY +from litellm.exceptions import GuardrailRaisedException +from litellm.integrations.prometheus import PrometheusLogger +from litellm.proxy._types import ProxyException +from litellm.proxy.common_utils.proxy_rate_limit_error import ProxyRateLimitError + + +@pytest.fixture(autouse=True) +def cleanup_prometheus_registry(): + for collector in list(REGISTRY._collector_to_names.keys()): + try: + REGISTRY.unregister(collector) + except Exception: + pass + + yield + + for collector in list(REGISTRY._collector_to_names.keys()): + try: + REGISTRY.unregister(collector) + except Exception: + pass + + +def _attributed_failure_kwargs(exception: Exception, rejected_before_routing: bool) -> dict: + return { + "model": "openai/gpt-4.1", + "litellm_params": { + "custom_llm_provider": "openai", + "metadata": {"model_info": {"id": "dep-1"}, "model_group": "internal-model"}, + **({PROXY_REJECTED_BEFORE_ROUTING_KEY: True} if rejected_before_routing else {}), + }, + "standard_logging_object": { + "model_id": "dep-1", + "model_group": "internal-model", + "api_base": "https://api.openai.com", + "metadata": {}, + }, + "exception": exception, + } + + +def _model_id_values(metric) -> set[str]: + index = metric._labelnames.index("model_id") + return {sample_key[index] for sample_key in metric._metrics} + + +class _ProviderError(Exception): + status_code = 500 + + +@pytest.mark.parametrize( + "rejection", + [ + HTTPException(status_code=403, detail="guardrail blocked"), + ProxyException(message="budget exceeded", type="budget_exceeded", param=None, code=400), + ProxyRateLimitError(detail={"error": "key rpm limit"}), + GuardrailRaisedException(guardrail_name="pii", message="blocked", status_code=403), + ], + ids=["http_exception", "proxy_exception", "proxy_rate_limit", "guardrail_raised"], +) +def test_attributed_proxy_reject_leaves_deployment_healthy(rejection: Exception): + logger = PrometheusLogger() + + logger.set_llm_deployment_failure_metrics(_attributed_failure_kwargs(rejection, rejected_before_routing=True)) + + assert logger.litellm_deployment_state._metrics == {} + assert _model_id_values(logger.litellm_deployment_failure_responses) == {""} + assert _model_id_values(logger.litellm_deployment_total_requests) == {""} + + +@pytest.mark.parametrize( + "failure", + [ + _ProviderError("upstream 500"), + GuardrailRaisedException(guardrail_name="pii", message="response blocked", status_code=400), + ], + ids=["provider_error", "post_call_guardrail"], +) +def test_failure_after_routing_still_marks_deployment_partial_outage(failure: Exception): + logger = PrometheusLogger() + + logger.set_llm_deployment_failure_metrics(_attributed_failure_kwargs(failure, rejected_before_routing=False)) + + assert _model_id_values(logger.litellm_deployment_state) == {"dep-1"} + assert _model_id_values(logger.litellm_deployment_failure_responses) == {"dep-1"} diff --git a/tests/test_litellm/integrations/test_prometheus_requested_model_cardinality.py b/tests/test_litellm/integrations/test_prometheus_requested_model_cardinality.py index 519a13751f1..f86f4460b28 100644 --- a/tests/test_litellm/integrations/test_prometheus_requested_model_cardinality.py +++ b/tests/test_litellm/integrations/test_prometheus_requested_model_cardinality.py @@ -116,6 +116,22 @@ async def test_unknown_models_collapse_to_one_series_on_proxy_request_metrics(ro assert _total_value(metric) == 25 +@pytest.mark.asyncio +@pytest.mark.parametrize("model", [["gpt-4o-mini"], {"name": "gpt-4o-mini"}, 123]) +async def test_non_string_models_collapse_to_other_on_proxy_request_metrics(router, model: object): + logger = PrometheusLogger() + + with patch("litellm.proxy.proxy_server.llm_router", router, create=True): # test-quality-ok: production reads proxy_server.llm_router lazily, no injection seam + await logger.async_post_call_failure_hook( + request_data={"model": model, "metadata": {}, "proxy_server_request": {}}, + original_exception=_ClientSideError("'model' must be a string."), + user_api_key_dict=UserAPIKeyAuth(api_key="hashed-key-1"), + ) + + assert _requested_model_values(logger.litellm_proxy_failed_requests_metric) == {UNRECOGNIZED_REQUESTED_MODEL_LABEL} + assert _total_value(logger.litellm_proxy_failed_requests_metric) == 1 + + @pytest.mark.asyncio async def test_known_alias_and_wildcard_models_keep_their_own_labels(router): logger = PrometheusLogger() diff --git a/tests/test_litellm/proxy/utils/proxy_logging/test_post_call_failure_hook.py b/tests/test_litellm/proxy/utils/proxy_logging/test_post_call_failure_hook.py index a4bb7d63548..d7c52c528eb 100644 --- a/tests/test_litellm/proxy/utils/proxy_logging/test_post_call_failure_hook.py +++ b/tests/test_litellm/proxy/utils/proxy_logging/test_post_call_failure_hook.py @@ -5,16 +5,18 @@ from __future__ import annotations import asyncio from datetime import datetime -from typing import Any, Final +from types import MappingProxyType +from typing import Final from unittest.mock import AsyncMock, MagicMock import pytest from fastapi import HTTPException import litellm +from litellm.constants import PROXY_REJECTED_BEFORE_ROUTING_KEY from litellm.exceptions import GuardrailRaisedException from litellm.integrations.custom_logger import CustomLogger -from litellm.proxy._types import AlertType, ProxyErrorTypes, UserAPIKeyAuth +from litellm.proxy._types import ProxyErrorTypes, UserAPIKeyAuth from litellm.proxy.utils import ProxyLogging @@ -99,6 +101,456 @@ async def test_post_call_failure_hook_no_callbacks_returns_none( } +@pytest.mark.asyncio +async def test_post_call_failure_hook_attributes_single_router_deployment( + proxy_logging, make_user_api_key_auth, monkeypatch +): + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + "model_info": {"provider": "acme"}, + } + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={"model": "internal-model", "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=403, detail="blocked"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs["custom_llm_provider"] == "openai" + assert kwargs["litellm_params"]["custom_llm_provider"] == "openai" + assert kwargs["litellm_params"]["metadata"]["model_info"]["provider"] == "acme" + assert kwargs["litellm_params"]["metadata"]["deployment"] == "openai/gpt-4.1" + assert kwargs["litellm_params"][PROXY_REJECTED_BEFORE_ROUTING_KEY] is True + assert kwargs["standard_logging_object"]["custom_llm_provider"] == "openai" + assert ( + kwargs["standard_logging_object"]["model_id"] == proxy_server.llm_router.get_model_list()[0]["model_info"]["id"] + ) + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_keeps_router_stamped_metadata_for_post_call_failures( + proxy_logging, make_user_api_key_auth, monkeypatch +): + """A post-call guardrail block arrives after the provider handoff with the router's own + ``model_info`` in the request metadata. The pre-routing flag must stay off so deployment + metrics keep attributing the failure to the deployment that actually served the call.""" + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + "model_info": {"id": "routed-deployment"}, + } + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + request_data = { + "litellm_call_id": "post-call-guardrail", + "model": "internal-model", + "messages": [{"role": "user", "content": "hi"}], + "metadata": {"model_info": {"id": "routed-deployment", "served": True}}, + } + logging_obj, request_data = litellm.utils.function_setup( + original_function="acompletion", rules_obj=litellm.utils.Rules(), start_time=datetime.now(), **request_data + ) + logging_obj.model_call_details["first_api_call_start_time"] = datetime.now() + request_data["litellm_logging_obj"] = logging_obj + + await proxy_logging.post_call_failure_hook( + request_data=request_data, + original_exception=GuardrailRaisedException(guardrail_name="g", message="response blocked"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs["litellm_params"]["metadata"]["model_info"] == {"id": "routed-deployment", "served": True} + assert PROXY_REJECTED_BEFORE_ROUTING_KEY not in kwargs["litellm_params"] + assert kwargs["standard_logging_object"]["model_id"] == "routed-deployment" + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_flags_pre_routing_reject_despite_caller_model_info( + proxy_logging, make_user_api_key_auth, monkeypatch +): + """A key allowed to override pricing keeps caller-supplied ``metadata.model_info``. A reject + before any provider handoff must still carry the pre-routing flag so deployment metrics do + not record an outage for a deployment the request never reached.""" + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + "model_info": {"id": "real-deployment"}, + } + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={ + "model": "internal-model", + "messages": [{"role": "user", "content": "hi"}], + "metadata": {"model_info": {"id": "spoofed-deployment"}}, + }, + original_exception=HTTPException(status_code=429, detail="key over limit"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs["litellm_params"][PROXY_REJECTED_BEFORE_ROUTING_KEY] is True + assert kwargs["litellm_params"]["custom_llm_provider"] == "openai" + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_attribution_does_not_count_against_the_deployment( + proxy_logging, make_user_api_key_auth, monkeypatch +): + """The router's failure callbacks run on this path too. A proxy-side reject must not + bump the deployment's failure or rpm counters, or a key hitting its own limit + could cool down the only deployment for everyone.""" + from litellm.proxy import proxy_server + + router = litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test", "rpm": 100}, + } + ] + ) + monkeypatch.setattr(proxy_server, "llm_router", router) + proxy_logging.alert_types = [] + deployment_id = router.get_model_list()[0]["model_info"]["id"] + + for status in (403, 429): + await proxy_logging.post_call_failure_hook( + request_data={"model": "internal-model", "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=status, detail="blocked"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + pending = asyncio.all_tasks() - {asyncio.current_task()} + await asyncio.gather(*pending, return_exceptions=True) + + deployment_keys = [key for key in router.cache.in_memory_cache.cache_dict if deployment_id in key] + assert deployment_keys == [], f"proxy reject was counted against the deployment: {deployment_keys}" + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_attributes_the_keys_team_deployment_over_the_global_group( + proxy_logging, make_user_api_key_auth, monkeypatch +): + """A team key requesting its team public model name must be attributed to the team's + deployment, not to a global group that happens to share the public name.""" + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "shared-name", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + "model_info": {"id": "global-deployment"}, + }, + { + "model_name": "shared-name_test-team_deadbeef", + "litellm_params": {"model": "anthropic/claude-sonnet-4-5", "api_key": "sk-test"}, + "model_info": { + "id": "team-deployment", + "team_id": "test-team", + "team_public_model_name": "shared-name", + }, + }, + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={"model": "shared-name", "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=429, detail="rate limited"), + user_api_key_dict=make_user_api_key_auth(team_id="test-team", request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs["custom_llm_provider"] == "anthropic" + assert kwargs["litellm_params"]["metadata"]["deployment"] == "anthropic/claude-sonnet-4-5" + assert kwargs["standard_logging_object"]["model_id"] == "team-deployment" + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_omits_provider_for_mixed_router_deployments( + proxy_logging, make_user_api_key_auth, monkeypatch +): + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + }, + { + "model_name": "internal-model", + "litellm_params": {"model": "anthropic/claude-sonnet-4-5", "api_key": "sk-test"}, + }, + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={"model": "internal-model", "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=403, detail="blocked"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs.get("custom_llm_provider") is None + assert "model_info" not in (kwargs["litellm_params"].get("metadata") or {}) + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_omits_provider_when_a_deployment_does_not_resolve( + proxy_logging, make_user_api_key_auth, monkeypatch +): + """One deployment resolves to openai and its sibling resolves to nothing: the group + is not known to be single-provider, so no provider is stamped on the failure.""" + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + router = MagicMock() + router.get_model_list.return_value = [ + {"model_name": "internal-model", "litellm_params": {"model": "openai/gpt-4.1"}}, + {"model_name": "internal-model", "litellm_params": {"model": "unmapped-model-with-no-provider"}}, + ] + monkeypatch.setattr(proxy_server, "llm_router", router) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={"model": "internal-model", "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=403, detail="blocked"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs.get("custom_llm_provider") is None + assert kwargs["litellm_params"].get("custom_llm_provider") is None + + +@pytest.mark.asyncio +async def test_handle_logging_proxy_only_path_attributes_with_read_only_metadata( + proxy_logging, make_user_api_key_auth, monkeypatch +): + """With a logging object already on the request, its metadata is taken as given; + a read-only mapping there must not crash the stamp, and the failure handler + still receives the provider attribution.""" + from litellm.proxy import proxy_server + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + "model_info": {"provider": "acme"}, + } + ] + ), + ) + logging_obj = MagicMock() + logging_obj.call_type = "acompletion" + logging_obj.model_call_details = {} + logging_obj.async_failure_handler = AsyncMock() + + await proxy_logging._handle_logging_proxy_only_error( + request_data={ + "litellm_logging_obj": logging_obj, + "model": "internal-model", + "messages": [{"role": "user", "content": "hi"}], + "metadata": MappingProxyType({"user_api_key_alias": "frozen"}), + }, + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + original_exception=HTTPException(status_code=403, detail="blocked"), + ) + + assert logging_obj.async_failure_handler.called + update_kwargs = logging_obj.update_environment_variables.call_args.kwargs + assert update_kwargs["custom_llm_provider"] == "openai" + assert update_kwargs["litellm_params"]["custom_llm_provider"] == "openai" + assert update_kwargs["litellm_params"]["metadata"] == {"user_api_key_alias": "frozen"} + + +@pytest.mark.asyncio +async def test_post_call_failure_hook_fires_without_router_attribution( + proxy_logging, make_user_api_key_auth, monkeypatch +): + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "different-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + } + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={"model": "internal-model", "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=403, detail="blocked"), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs.get("custom_llm_provider") is None + assert "model_info" not in (kwargs["litellm_params"].get("metadata") or {}) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("model", [123, ["internal-model"], {"name": "internal-model"}, None]) +async def test_post_call_failure_hook_fires_for_non_string_model( + proxy_logging, make_user_api_key_auth, monkeypatch, model: object +): + """A body whose ``model`` is not a string is rejected by the proxy before routing; its + failure callback must still fire, unattributed, instead of a TypeError escaping the hook.""" + from litellm.proxy import proxy_server + + recorded: list[dict] = [] + + class _RecordingLogger(CustomLogger): + async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + recorded.append(kwargs) + + monkeypatch.setattr( + proxy_server, + "llm_router", + litellm.Router( + model_list=[ + { + "model_name": "internal-model", + "litellm_params": {"model": "openai/gpt-4.1", "api_key": "sk-test"}, + } + ] + ), + ) + monkeypatch.setattr(litellm, "callbacks", [_RecordingLogger()]) + proxy_logging.alert_types = [] + + await proxy_logging.post_call_failure_hook( + request_data={"model": model, "messages": [{"role": "user", "content": "hi"}]}, + original_exception=HTTPException(status_code=400, detail="'model' must be a string."), + user_api_key_dict=make_user_api_key_auth(request_route="/chat/completions"), + route="/chat/completions", + ) + + assert len(recorded) == 1 + kwargs = recorded[0] + assert kwargs.get("custom_llm_provider") is None + assert "model_info" not in (kwargs["litellm_params"].get("metadata") or {}) + + @pytest.mark.asyncio async def test_post_call_failure_hook_callback_returns_http_exception( proxy_logging, make_user_api_key_auth, monkeypatch From 075536eca1a247bbab78d7992275a176875b96ae Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 21:19:26 +0000 Subject: [PATCH 07/11] chore(cost-map): remove models past their deprecation date (#42435) * chore(cost-map): remove models past their deprecation date Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(cost-calc): drop the empty parametrize left behind by the gemini web search removal Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): drop merge base block left by conflict resolution Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(cost-calc): drop gemini image cost tests pinned on removed model Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: kerry Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 6095 +---------------- model_prices_and_context_window.json | 6095 +---------------- .../test_anthropic_cache_control_hook.py | 2 +- .../llm_cost_calc/test_llm_cost_calc_utils.py | 151 - .../test_tool_call_cost_tracking.py | 123 - .../test_fallback_generalizations.py | 4 - .../test_get_model_cost_map.py | 1 - .../test_litellm_logging.py | 15 - ...streaming_chunk_builder_server_tool_use.py | 26 - .../litellm_core_utils/test_token_counter.py | 3 - .../chat/test_converse_transformation.py | 37 - .../test_databricks_cost_calculator.py | 8 - .../llms/gemini/test_cost_calculator.py | 195 - .../test_github_copilot_transformation.py | 54 - .../llms/openai/test_gpt5_transformation.py | 16 - ...test_vertex_and_google_ai_studio_gemini.py | 4 +- ...test_vertex_passthrough_logging_handler.py | 28 - .../wandb/test_wandb_chat_transformation.py | 4 - .../llms/xai/test_xai_cost_calculator.py | 73 - .../xai/test_xai_redirected_slug_pricing.py | 102 - .../proxy/auth/test_auth_checks.py | 1 - ...t_anthropic_passthrough_logging_handler.py | 73 - .../test_vertex_ai_batch_passthrough.py | 232 - .../proxy/spend_tracking/test_savings.py | 19 - .../test_spend_management_endpoints.py | 172 - .../responses/test_metadata_codex_callback.py | 66 - .../rust_bridge/test_token_counter.py | 1 - tests/test_litellm/test_cost_calculator.py | 374 - .../test_count_tokens_public_api.py | 18 - .../test_gpt_image_cost_calculator.py | 21 - tests/test_litellm/test_router.py | 30 - .../test_together_ai_model_metadata.py | 9 - tests/test_litellm/test_utils.py | 6 - .../test_xai_responses_auto_routing.py | 77 - .../chat/test_azure_ai_transformation.py | 21 - .../test_fireworks_ai_chat_transformation.py | 15 - .../test_moonshot_chat_transformation.py | 2 +- 37 files changed, 18 insertions(+), 14155 deletions(-) delete mode 100644 tests/test_litellm/llms/xai/test_xai_redirected_slug_pricing.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 431e965524e..b48bdd6322c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -53,13 +53,6 @@ "mode": "image_generation", "output_cost_per_image": 0.04 }, - "1024-x-1024/dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 1.9e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -67,13 +60,6 @@ "mode": "image_generation", "output_cost_per_image": 0.08 }, - "256-x-256/dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 2.4414e-07, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -81,13 +67,6 @@ "mode": "image_generation", "output_cost_per_image": 0.018 }, - "512-x-512/dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 6.86e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -961,23 +940,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -993,23 +955,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", @@ -2971,60 +2916,6 @@ "supports_vision": true, "supports_tool_choice": true }, - "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, - "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, @@ -3052,23 +2943,6 @@ "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06 }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -3446,29 +3320,6 @@ "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024 }, - "azure_ai/claude-opus-4-1": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "azure_ai/claude-sonnet-4-5": { "deprecation_date": "2026-10-19", "cache_creation_input_token_cost": 3.75e-06, @@ -4503,43 +4354,6 @@ "output_cost_per_token_priority": 2.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.375e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.375e-07, @@ -4832,43 +4646,6 @@ "output_cost_per_token_priority": 2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/global/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, @@ -4944,19 +4721,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-3.5-turbo-0125": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-3.5-turbo-instruct-0914": { "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_text", @@ -4976,32 +4740,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-35-turbo-0125": { - "deprecation_date": "2025-05-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-1106": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 1e-06, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-35-turbo-16k": { "input_cost_per_token": 3e-06, "litellm_provider": "azure", @@ -5769,40 +5507,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/gpt-realtime-2": { - "cache_read_input_audio_token_cost": 4e-07, - "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2026-08-31", - "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image_token": 5e-06, - "input_cost_per_token": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 6.4e-05, - "output_cost_per_token": 2.4e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, @@ -6100,45 +5804,6 @@ "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 }, - "azure/gpt-5.1-chat-2025-11-13": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, @@ -6289,73 +5954,6 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 6.25e-08 }, - "azure/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-03-17", @@ -6617,43 +6215,6 @@ "output_cost_per_token_priority": 2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, @@ -6832,78 +6393,6 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 8.75e-08 }, - "azure/gpt-5.2-chat": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5.2-chat-2025-12-11": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-05-13", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2027-07-13", @@ -6936,42 +6425,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5.3-chat": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, @@ -10563,43 +10016,6 @@ "output_cost_per_token_priority": 2.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.375e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.375e-07, @@ -11201,18 +10617,6 @@ "/v1/images/edits" ] }, - "azure_ai/MAI-Image-2e": { - "deprecation_date": "2026-08-15", - "input_cost_per_token": 5e-06, - "litellm_provider": "azure_ai", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "output_cost_per_image_token": 1.95e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, "azure_ai/MAI-Thinking-1": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, @@ -11237,34 +10641,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.7e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 2.04e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.04e-06, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure_ai/Llama-3.3-70B-Instruct": { "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", @@ -11313,18 +10689,6 @@ "output_cost_per_token": 3.7e-07, "supports_tool_choice": true }, - "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 5.33e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 1.6e-05, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, "azure_ai/Meta-Llama-3.1-70B-Instruct": { "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", @@ -11336,18 +10700,6 @@ "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.1e-07, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, "azure_ai/Phi-3-medium-128k-instruct": { "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", @@ -11518,16 +10870,6 @@ "supports_tool_choice": true, "supports_reasoning": true }, - "azure_ai/mistral-document-ai-2505": { - "deprecation_date": "2026-07-20", - "litellm_provider": "azure_ai", - "ocr_cost_per_page": 0.003, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr" - ], - "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" - }, "azure_ai/mistral-document-ai-2512": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, @@ -11628,17 +10970,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "azure_ai/cohere-rerank-v3.5": { - "deprecation_date": "2026-05-14", - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 - }, "azure_ai/cohere-rerank-v4.0-pro": { "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, @@ -11691,19 +11022,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/deepseek-r1": { - "deprecation_date": "2026-08-13", - "input_cost_per_token": 1.35e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_reasoning": true, - "supports_tool_choice": true - }, "azure_ai/deepseek-v3": { "input_cost_per_token": 1.14e-06, "litellm_provider": "azure_ai", @@ -11715,33 +11033,6 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, - "azure_ai/deepseek-v3-0324": { - "deprecation_date": "2026-07-13", - "input_cost_per_token": 1.14e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/deepseek-v3.1": { - "deprecation_date": "2026-07-13", - "input_cost_per_token": 1.23e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.94e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "azure_ai/deepseek-v4-pro": { "deprecation_date": "2028-02-20", "input_cost_per_token": 1.74e-06, @@ -11808,68 +11099,6 @@ ], "supports_embedding_image_input": true }, - "azure_ai/global/grok-3": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/global/grok-3-mini": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3-mini": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", @@ -11963,36 +11192,6 @@ "supports_vision": true, "supports_web_search": true }, - "azure_ai/grok-4-fast-non-reasoning": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-4-fast-reasoning": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/grok-4-1-fast-non-reasoning": { "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, @@ -13516,40 +12715,6 @@ "mode": "chat", "output_cost_per_token": 1.5e-06 }, - "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-07, - "cache_creation_input_token_cost": 4.5e-06 - }, - "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, @@ -13727,61 +12892,6 @@ "mode": "chat", "output_cost_per_token": 1.5e-06 }, - "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 4.5e-06, - "cache_read_input_token_cost": 3.6e-07, - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-07, - "cache_creation_input_token_cost": 4.5e-06 - }, - "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, @@ -14219,34 +13329,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "cerebras/zai-glm-4.6": { - "deprecation_date": "2026-01-20", - "input_cost_per_token": 2.25e-06, - "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-06, - "source": "https://www.cerebras.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "cerebras/zai-glm-4.7": { - "deprecation_date": "2026-08-17", - "input_cost_per_token": 2.25e-06, - "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-06, - "source": "https://www.cerebras.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "cerebras/qwen-3.8-27b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", @@ -14272,23 +13354,6 @@ "mode": "chat", "output_cost_per_token": 5e-07 }, - "chatgpt-4o-latest": { - "deprecation_date": "2026-02-17", - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-transcribe-diarize": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -14351,131 +13416,6 @@ "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-3-7-sonnet-20250219": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-02-19", - "input_cost_per_token": 3e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "claude-3-haiku-20240307": { - "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 5e-07, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-04-20", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-3-opus-20240229": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "deprecation_date": "2026-01-05", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-4-opus-20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "deprecation_date": "2026-06-15", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-4-sonnet-20250514": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "deprecation_date": "2026-06-15", - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "prompt_cache_min_tokens": 1024 - }, "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -14654,92 +13594,6 @@ "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06 }, - "claude-opus-4-1": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "deprecation_date": "2026-08-05" - }, - "claude-opus-4-1-20250805": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "deprecation_date": "2026-08-05", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-opus-4-20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "deprecation_date": "2026-06-15", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15167,38 +14021,6 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-sonnet-4-20250514": { - "deprecation_date": "2026-06-15", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", @@ -15551,36 +14373,6 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "codex-mini-latest": { - "cache_read_input_token_cost": 3.75e-07, - "deprecation_date": "2026-02-12", - "input_cost_per_token": 1.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 6e-06, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "cohere.command-light-text-v14": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", @@ -15680,16 +14472,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "command": { - "input_cost_per_token": 1e-06, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "completion", - "output_cost_per_token": 2e-06, - "deprecation_date": "2025-09-15" - }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", @@ -15716,17 +14498,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "command-light": { - "input_cost_per_token": 3e-07, - "litellm_provider": "cohere_chat", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-nightly": { "input_cost_per_token": 1e-06, "litellm_provider": "cohere", @@ -15736,18 +14507,6 @@ "mode": "completion", "output_cost_per_token": 2e-06 }, - "command-r": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_function_calling": true, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-r-08-2024": { "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", @@ -15759,18 +14518,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "command-r-plus": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-r-plus-08-2024": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", @@ -15823,26 +14570,6 @@ "supports_vision": true, "source": "https://platform.openai.com/docs/models/computer-use-preview" }, - "dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_image": 0.02, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations", - "/v1/images/edits", - "/v1/images/variations" - ] - }, - "dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_image": 0.04, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 2.8e-07, @@ -18839,30 +17566,6 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, - "databricks/databricks-claude-3-7-sonnet": { - "cache_creation_input_token_cost": 3.74997e-06, - "cache_read_input_token_cost": 3.0002e-07, - "deprecation_date": "2026-04-12", - "input_cost_per_token": 2.9999900000000002e-06, - "input_dbu_cost_per_token": 4.2857e-05, - "litellm_provider": "databricks", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_anthropic_thinking_payload": true, - "supports_tool_choice": true - }, "databricks/databricks-claude-fable-5": { "cache_creation_input_token_cost": 1.250004e-05, "cache_read_input_token_cost": 1.00002e-06, @@ -19825,44 +18528,6 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, - "databricks/databricks-gpt-5-1-codex-max": { - "cache_creation_input_token_cost": 1.24999e-06, - "cache_read_input_token_cost": 1.2502e-07, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 1.24999e-06, - "input_dbu_cost_per_token": 1.7857e-05, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, - "output_dbu_cost_per_token": 0.000142857, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, - "databricks/databricks-gpt-5-1-codex-mini": { - "cache_creation_input_token_cost": 2.4997e-07, - "cache_read_input_token_cost": 2.499e-08, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 2.4997e-07, - "input_dbu_cost_per_token": 3.571e-06, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.99997e-06, - "output_dbu_cost_per_token": 2.8571e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, "databricks/databricks-gpt-5-2": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, @@ -19883,25 +18548,6 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, - "databricks/databricks-gpt-5-2-codex": { - "cache_creation_input_token_cost": 1.75e-06, - "cache_read_input_token_cost": 1.75e-07, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 1.75e-06, - "input_dbu_cost_per_token": 2.5e-05, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_dbu_cost_per_token": 0.0002, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, "databricks/databricks-gpt-5-3-codex": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, @@ -20328,25 +18974,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "databricks/databricks-llama-2-70b-chat": { - "cache_creation_input_token_cost": 5.0001e-07, - "cache_read_input_token_cost": 5.0001e-07, - "deprecation_date": "2024-10-30", - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, - "output_dbu_cost_per_token": 2.1429e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-llama-4-maverick": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, @@ -20365,25 +18992,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-1-405b-instruct": { - "cache_creation_input_token_cost": 5.00003e-06, - "cache_read_input_token_cost": 5.00003e-06, - "deprecation_date": "2026-02-15", - "input_cost_per_token": 5.00003e-06, - "input_dbu_cost_per_token": 7.1429e-05, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, @@ -20419,82 +19027,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-70b-instruct": { - "cache_creation_input_token_cost": 1.00002e-06, - "cache_read_input_token_cost": 1.00002e-06, - "deprecation_date": "2024-07-23", - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 2.9999900000000002e-06, - "output_dbu_cost_per_token": 4.2857e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mixtral-8x7b-instruct": { - "cache_creation_input_token_cost": 5.0001e-07, - "cache_read_input_token_cost": 5.0001e-07, - "deprecation_date": "2025-04-30", - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.00002e-06, - "output_dbu_cost_per_token": 1.4286e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-30b-instruct": { - "cache_creation_input_token_cost": 1.00002e-06, - "cache_read_input_token_cost": 1.00002e-06, - "deprecation_date": "2024-08-30", - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.00002e-06, - "output_dbu_cost_per_token": 1.4286e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-7b-instruct": { - "cache_creation_input_token_cost": 5.0001e-07, - "cache_read_input_token_cost": 5.0001e-07, - "deprecation_date": "2024-08-30", - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-qwen35-122b-a10b": { "cache_creation_input_token_cost": 2.2001e-07, "cache_read_input_token_cost": 2.2001e-07, @@ -21559,18 +20091,6 @@ "supports_tool_choice": true, "supports_function_calling": true }, - "deepinfra/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_function_calling": true - }, "deepinfra/google/gemini-2.5-flash": { "max_tokens": 1000000, "max_input_tokens": 1000000, @@ -22429,15 +20949,6 @@ "/v1/audio/speech" ] }, - "embed-english-light-v2.0": { - "deprecation_date": "2026-04-04", - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", @@ -22446,15 +20957,6 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, - "embed-english-v2.0": { - "deprecation_date": "2026-04-04", - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_tokens": 4096, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-english-v3.0": { "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, @@ -22469,15 +20971,6 @@ "supports_embedding_image_input": true, "supports_image_input": true }, - "embed-multilingual-v2.0": { - "deprecation_date": "2026-04-04", - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 768, - "max_tokens": 768, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", @@ -22645,23 +21138,6 @@ "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -22677,23 +21153,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, @@ -25265,26 +23724,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { - "cache_read_input_token_cost": 6e-07, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 1.2e-06, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "cache_read_input_token_cost_priority": 5.5e-08, @@ -25672,26 +24111,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { - "cache_read_input_token_cost": 6e-08, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 3e-07, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, @@ -25779,26 +24198,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/deepseek-v4-pro": { - "cache_read_input_token_cost": 6e-07, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 1.2e-06, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, @@ -25998,26 +24397,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/minimax-m2p7": { - "cache_read_input_token_cost": 6e-08, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 3e-07, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, @@ -26195,31 +24574,6 @@ "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B": { - "litellm_provider": "friendliai", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 1.2e-07, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "Frontier-scale multilingual language model developed by LG AI Research", - "deprecation_date": "2026-09-06", - "source": "https://api.friendli.ai/serverless/v1/models" - }, "friendliai/deepseek-ai/DeepSeek-V3.2": { "litellm_provider": "friendliai", "max_input_tokens": 163840, @@ -26525,160 +24879,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_character": 3.75e-08, - "input_cost_per_token": 1.5e-07, - "input_cost_per_token_batches": 7.5e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_batches": 3e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-001": { - "cache_read_input_token_cost": 3.75e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_audio_token_batches": 3.75e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_batches": 3.75e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "output_cost_per_token_batches": 1.5e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, "deprecation_date": "2026-10-20", @@ -27503,53 +25703,6 @@ }, "gemini_native_audio": true }, - "gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, "gemini-2.5-pro": { "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1.25e-07, @@ -27608,62 +25761,6 @@ "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05 }, - "gemini-3-pro-preview": { - "deprecation_date": "2026-03-26", - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, @@ -28322,51 +26419,6 @@ "supports_url_context": true, "supports_vision": true }, - "gemini/gemini-robotics-er-1.5-preview": { - "cache_read_input_token_cost": 0, - "deprecation_date": "2026-04-30", - "input_cost_per_token": 3e-07, - "input_cost_per_audio_token": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "video", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "rpm": 10, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini/gemini-robotics-er-2-preview": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, @@ -28417,53 +26469,6 @@ "supports_web_search": true, "web_search_billing_unit": "per_query" }, - "gemini/gemini-robotics-er-1.6-preview": { - "deprecation_date": "2026-08-31", - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 5e-06, - "output_cost_per_token": 5e-06, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "web_search_billing_unit": "per_query" - }, "gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, @@ -28600,27 +26605,6 @@ "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", "tpm": 10000000 }, - "gemini/gemini-embedding-2-preview": { - "deprecation_date": "2026-08-10", - "input_cost_per_audio_token": 6.5e-06, - "input_cost_per_audio_token_batches": 3.25e-06, - "input_cost_per_image_token": 4.5e-07, - "input_cost_per_image_token_batches": 2.25e-07, - "input_cost_per_token": 2e-07, - "input_cost_per_token_batches": 1e-07, - "input_cost_per_video_token": 1.2e-05, - "input_cost_per_video_token_batches": 6e-06, - "litellm_provider": "gemini", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supports_multimodal": true, - "tpm": 10000000 - }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, @@ -28643,135 +26627,6 @@ "supports_vision": true, "tpm": 10000000 }, - "gemini/gemini-1.5-flash": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", - "supports_multimodal": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-001": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini/gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 3e-08, @@ -28934,50 +26789,6 @@ "web_search_billing_unit": "per_query", "supports_reasoning": false }, - "gemini/gemini-3-pro-image-preview": { - "deprecation_date": "2026-06-25", - "input_cost_per_image": 0.0011, - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, - "output_cost_per_token": 1.2e-05, - "rpm": 1000, - "tpm": 4000000, - "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -29063,49 +26874,6 @@ }, "web_search_billing_unit": "per_query" }, - "gemini/gemini-3.1-flash-image-preview": { - "deprecation_date": "2026-06-25", - "input_cost_per_token": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.045, - "output_cost_per_image_token": 6e-05, - "output_cost_per_token": 3e-06, - "output_cost_per_token_batches": 1.5e-06, - "rpm": 1000, - "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, @@ -29244,104 +27012,6 @@ "supports_audio_input": true, "supports_image_size": false }, - "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 1e-08, - "deprecation_date": "2026-03-31", - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-02-17", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, @@ -29459,55 +27129,6 @@ "supports_video_input": true, "web_search_billing_unit": "per_query" }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, "gemini/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, @@ -29618,114 +27239,6 @@ "supports_vision": true, "tpm": 800000 }, - "gemini/gemini-3-pro-preview": { - "deprecation_date": "2026-03-09", - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-05-25", - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 - }, "gemini/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, @@ -30826,34 +28339,6 @@ "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "gemini/imagen-3.0-generate-002": { - "deprecation_date": "2025-11-10", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-fast-generate-001": { - "deprecation_date": "2026-08-17", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-generate-001": { - "deprecation_date": "2026-08-17", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-ultra-generate-001": { - "deprecation_date": "2026-08-17", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, "gemini/learnlm-1.5-pro-experimental": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -30932,21 +28417,6 @@ "supports_web_search": false, "output_cost_per_image": 0.08 }, - "gemini/veo-2.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "gemini", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.35, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, "gemini/veo-3.1-fast-generate-preview": { "litellm_provider": "gemini", "max_input_tokens": 1024, @@ -32156,33 +29626,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-0125-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 3e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0314": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 3e-05, - "litellm_provider": "openai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4-0613": { "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-05, @@ -32252,22 +29695,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-turbo-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 3e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4.1": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, @@ -32610,24 +30037,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-audio-preview": { - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 4e-05, @@ -32812,44 +30221,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "gpt-audio-mini-2025-10-06": { - "deprecation_date": "2026-07-23", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, "gpt-audio-mini-2025-12-15": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, @@ -32946,24 +30317,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-mini-audio-preview": { - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 6e-07, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1e-05, @@ -32982,26 +30335,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4o-mini-realtime-preview": { - "cache_creation_input_audio_token_cost": 3e-07, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, @@ -33048,32 +30381,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-mini-search-preview-2025-03-11": { - "cache_read_input_token_cost": 7.5e-08, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.5e-07, - "input_cost_per_token_batches": 7.5e-08, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_batches": 3e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.025, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.025 - }, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -33108,63 +30415,6 @@ "audio" ] }, - "gpt-4o-realtime-preview": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2025-06-03": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -33191,32 +30441,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-search-preview-2025-03-11": { - "cache_read_input_token_cost": 1.25e-06, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_batches": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_batches": 5e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.025, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.025 - }, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -33879,52 +31103,6 @@ "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false }, - "gpt-5.1-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, @@ -34031,94 +31209,6 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, - "gpt-5.2-chat-latest": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-08-10", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.3-chat-latest": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-08-10", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, "gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, "input_cost_per_token_batches": 1.05e-05, @@ -35783,251 +32873,6 @@ "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, - "gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex-mini": { - "cache_read_input_token_cost": 2.5e-08, - "cache_read_input_token_cost_priority": 4.5e-08, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_priority": 4.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 2e-06, - "output_cost_per_token_priority": 3.6e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, "gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, @@ -36870,32 +33715,6 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/llama-3.1-8b-instant": { - "deprecation_date": "2026-08-16", - "input_cost_per_token": 5e-08, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-versatile": { - "deprecation_date": "2026-08-16", - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/llama-guard-3-8b": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", @@ -36905,19 +33724,6 @@ "output_cost_per_token": 2e-07, "source": "https://console.groq.com/docs/model/llama-guard-3-8b" }, - "groq/gemma-7b-it": { - "deprecation_date": "2024-12-18", - "input_cost_per_token": 5e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/meta-llama/llama-prompt-guard-2-22m": { "input_cost_per_token": 3e-08, "litellm_provider": "groq", @@ -36938,58 +33744,6 @@ "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" }, - "groq/meta-llama/llama-guard-4-12b": { - "deprecation_date": "2026-03-05", - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07 - }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "deprecation_date": "2026-03-09", - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "deprecation_date": "2026-07-17", - "input_cost_per_token": 1.1e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3.4e-07, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/moonshotai/kimi-k2-instruct-0905": { - "deprecation_date": "2026-04-15", - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "groq", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "groq/openai/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, @@ -37070,45 +33824,6 @@ "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, - "groq/playai-tts": { - "deprecation_date": "2025-12-31", - "input_cost_per_character": 5e-05, - "litellm_provider": "groq", - "max_input_tokens": 10000, - "max_output_tokens": 10000, - "max_tokens": 10000, - "mode": "audio_speech" - }, - "groq/qwen/qwen3.6-27b": { - "input_cost_per_token": 6e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://console.groq.com/docs/model/qwen/qwen3.6-27b", - "deprecation_date": "2026-09-14", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/qwen/qwen3-32b": { - "deprecation_date": "2026-07-17", - "input_cost_per_token": 2.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 5.9e-07, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/whisper-large-v3": { "input_cost_per_second": 3.083e-05, "litellm_provider": "groq", @@ -37121,27 +33836,6 @@ "mode": "audio_transcription", "output_cost_per_second": 0.0 }, - "hd/1024-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 7.629e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "hd/1024-x-1792/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 6.539e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "hd/1792-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 6.539e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", "max_tokens": 8192, @@ -38968,19 +35662,6 @@ "supports_system_messages": true, "supports_native_structured_output": true }, - "mistral/codestral-2405": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 1e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 3e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/codestral-2508": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, @@ -39024,51 +35705,6 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "mistral/devstral-medium-2507": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2505": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2507": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-small-latest": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, @@ -39084,21 +35720,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/labs-devstral-small-2512": { - "deprecation_date": "2026-03-31", - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-latest": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, @@ -39129,21 +35750,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/devstral-2512": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/ministral-14b-2512": { "input_cost_per_token": 2e-07, "litellm_provider": "mistral", @@ -39419,54 +36025,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/magistral-medium-2506": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-medium-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-medium-1-2-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-ocr-latest": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, @@ -39506,20 +36064,6 @@ "/v1/batch" ] }, - "mistral/mistral-ocr-2505-completion": { - "deprecation_date": "2026-05-31", - "litellm_provider": "mistral", - "ocr_cost_per_page": 0.001, - "ocr_cost_per_page_batches": 0.0005, - "annotation_cost_per_page": 0.003, - "annotation_cost_per_page_batches": 0.0015, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr", - "/v1/batch" - ], - "source": "https://mistral.ai/pricing#api-pricing" - }, "mistral/mistral-ocr-2512": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.002, @@ -39550,22 +36094,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/magistral-small-2506": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/magistral-small-latest": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, @@ -39583,22 +36111,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/magistral-small-1-2-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-embed": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", @@ -39622,48 +36134,6 @@ "max_tokens": 8192, "mode": "embedding" }, - "mistral/mistral-large-2402": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 4e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2407": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2411": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-large-latest": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, @@ -39733,49 +36203,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-2312": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 2.7e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 8.1e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2505": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2508": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-2604": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, @@ -39818,22 +36245,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-3-1-2508": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-3-5": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, @@ -39890,22 +36301,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-small-3-2-2506": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 6e-08, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/ministral-3-3b-2512": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, @@ -39999,32 +36394,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/open-codestral-mamba": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-7b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/open-mistral-nemo": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, @@ -40039,78 +36408,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/open-mistral-nemo-2407": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x22b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x7b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 7e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/pixtral-12b-2409": { - "deprecation_date": "2025-12-31", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/pixtral-large-2411": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/pixtral-large-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, @@ -40159,36 +36456,6 @@ "supports_audio_input": false, "supports_response_schema": true }, - "moonshot/kimi-k2-0711-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-0905-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "moonshot/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, @@ -40207,21 +36474,6 @@ "supports_video_input": true, "supports_vision": true }, - "moonshot/kimi-k2-turbo-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 1.15e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, @@ -40278,111 +36530,6 @@ "supports_video_input": true, "supports_vision": true }, - "moonshot/kimi-latest": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-128k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-32k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-8k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-thinking-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2025-11-11", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_vision": true - }, - "moonshot/kimi-k2-thinking": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-thinking-turbo": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 1.15e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "moonshot/moonshot-v1-128k": { "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -40396,19 +36543,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-128k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-128k-vision-preview": { "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -40436,19 +36570,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-32k-vision-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", @@ -40476,19 +36597,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-8k-vision-preview": { "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", @@ -41679,88 +37787,6 @@ "supports_vision": true, "supports_web_search": true }, - "o3-deep-research": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1e-05, - "input_cost_per_token_batches": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "output_cost_per_token_batches": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o3-deep-research-2025-06-26": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1e-05, - "input_cost_per_token_batches": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "output_cost_per_token_batches": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "o3-mini": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-10-23", @@ -41946,88 +37972,6 @@ "supports_vision": true, "supports_web_search": true }, - "o4-mini-deep-research": { - "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o4-mini-deep-research-2025-06-26": { - "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "oci/meta.llama-3.1-8b-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", @@ -43509,23 +39453,6 @@ "supports_vision": false, "supports_web_search": false }, - "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "openrouter/google/gemini-2.5-flash": { "cache_creation_input_token_cost": 8.33333333333333e-08, "cache_read_input_audio_token_cost": 1e-07, @@ -46699,17 +42626,6 @@ "supports_reasoning": true, "supports_system_messages": true }, - "rerank-english-v2.0": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0, - "deprecation_date": "2025-04-30" - }, "rerank-english-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, @@ -46720,17 +42636,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "rerank-multilingual-v2.0": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0, - "deprecation_date": "2025-04-30" - }, "rerank-multilingual-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, @@ -46871,31 +42776,6 @@ "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2026-03-20", - "input_cost_per_token": 7e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 3e-06, - "litellm_provider": "sambanova", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/Llama-4-Maverick-17B-128E-Instruct": { "input_cost_per_token": 6.3e-07, "litellm_provider": "sambanova", @@ -46913,73 +42793,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 4e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - }, - "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-06, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 1e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 4e-08, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-08, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 8e-08, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.6e-07, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, "sambanova/Meta-Llama-3.3-70B-Instruct": { "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", @@ -46993,54 +42806,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "sambanova/Meta-Llama-Guard-3-8B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 3e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/QwQ-32B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 5e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_audio_input": true - }, - "sambanova/Qwen3-32B": { - "deprecation_date": "2026-04-06", - "input_cost_per_token": 4e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/DeepSeek-V3.1": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -47633,27 +43398,6 @@ "mode": "image_generation", "output_cost_per_image": 0.14 }, - "standard/1024-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 3.81469e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "standard/1024-x-1792/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 4.359e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "standard/1792-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 4.359e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "linkup/search": { "input_cost_per_query": 0.00587, "litellm_provider": "linkup", @@ -47788,36 +43532,6 @@ "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "text-moderation-007": { - "deprecation_date": "2025-10-27", - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "text-moderation-latest": { - "deprecation_date": "2025-10-27", - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "text-moderation-stable": { - "deprecation_date": "2025-10-27", - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, "text-multilingual-embedding-002": { "deprecation_date": "2027-04-01", "input_cost_per_character": 2.5e-08, @@ -47915,19 +43629,6 @@ "mode": "chat", "output_cost_per_token": 1e-07 }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "max_input_tokens": 131072, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", "mode": "chat", @@ -47940,87 +43641,6 @@ "max_input_tokens": 32768, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "deprecation_date": "2026-07-10", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_tool_choice": false - }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "deprecation_date": "2026-06-04", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 3e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, - "metadata": { - "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" - }, - "mode": "chat", - "output_cost_per_token": 7e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "deprecation_date": "2026-02-03", - "input_cost_per_token": 5.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.19e-06, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", @@ -48037,33 +43657,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_tokens": 16384, - "metadata": { - "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" - }, - "mode": "chat", - "output_cost_per_token": 1.7e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "max_input_tokens": 131072, - "max_output_tokens": 16384 - }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", @@ -48077,112 +43670,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 0, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "deprecation_date": "2026-03-31", - "input_cost_per_token": 2.7e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.5e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 5.9e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 3.5e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 3.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "deprecation_date": "2025-11-13", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "max_input_tokens": 32768, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "deprecation_date": "2026-04-02", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_input_tokens": 32768, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/moonshotai/Kimi-K2-Instruct": { "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", @@ -48211,19 +43698,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 5e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/togethercomputer/CodeLlama-34b-Instruct": { "litellm_provider": "together_ai", "mode": "chat", @@ -48231,19 +43705,6 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.1e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", @@ -48260,102 +43721,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.7": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 4.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "max_tokens": 202752, - "metadata": { - "successor": "together_ai/zai-org/GLM-5.2" - }, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "together_ai/moonshotai/Kimi-K2.5": { - "deprecation_date": "2026-05-21", - "input_cost_per_token": 5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "max_tokens": 256000, - "metadata": { - "successor": "together_ai/moonshotai/Kimi-K3" - }, - "mode": "chat", - "output_cost_per_token": 2.8e-06, - "source": "https://www.together.ai/models/kimi-k2-5", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_reasoning": true - }, - "together_ai/moonshotai/Kimi-K2-Instruct-0905": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 1e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/moonshotai/Kimi-K3" - }, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://www.together.ai/models/kimi-k2-0905", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/Qwen/Qwen3.7-Plus" - }, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/Qwen/Qwen3.6-Plus" - }, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3.5-397B-A17B": { - "cache_read_input_token_cost": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, @@ -48477,23 +43842,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V4-Pro": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.74e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 512000, - "max_tokens": 512000, - "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, "deprecation_date": "2026-09-29", @@ -48510,52 +43858,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/google/gemma-3n-E4B-it": { - "deprecation_date": "2026-08-25", - "input_cost_per_token": 6e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.2e-07, - "source": "https://docs.together.ai/docs/serverless-models" - }, - "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 3.9e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 9.7e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 2e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 514, - "max_tokens": 514, - "mode": "embedding", - "output_cost_per_token": 2e-08, - "output_vector_size": 1024, - "source": "https://docs.together.ai/docs/serverless-models" - }, - "together_ai/meta-llama/Llama-Guard-4-12B": { - "deprecation_date": "2026-08-25", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.together.ai/docs/serverless-models" - }, "together_ai/meta-models/Muse-Glimmer-30B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, @@ -48567,23 +43869,6 @@ "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, - "together_ai/moonshotai/Kimi-K2.7-Code": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 1.9e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -48606,33 +43891,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 512288, - "max_tokens": 512288, - "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/pearl-ai/gemma-4-31b-it": { - "deprecation_date": "2026-08-27", - "input_cost_per_token": 2.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8.6e-07, - "source": "https://docs.together.ai/docs/serverless-models" - }, "together_ai/thinkingmachines/Inkling": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, @@ -48648,18 +43906,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-14", - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 524288, - "max_tokens": 524288, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models", - "supports_prompt_caching": true - }, "together_ai/zai-org/GLM-5.2": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, @@ -48923,23 +44169,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -48955,23 +44184,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, @@ -49036,23 +44248,6 @@ "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06 }, - "us-gov.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, @@ -50180,34 +45375,6 @@ "output_cost_per_token": 9e-07, "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, "vercel_ai_gateway/google/gemini-2.5-flash": { "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", @@ -51091,28 +46258,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-11", - "input_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-3-haiku": { "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", @@ -51191,72 +46336,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-opus-4": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-opus-4-1": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "output_cost_per_token_batches": 3.75e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "vertex_ai/claude-opus-4-1@20250805": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "output_cost_per_token_batches": 3.75e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, @@ -51857,98 +46936,6 @@ "supports_native_streaming": true, "prompt_cache_min_tokens": 1024 }, - "vertex_ai/claude-opus-4@20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-sonnet-4": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-sonnet-4@20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", @@ -52451,62 +47438,6 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "cache_read_input_token_cost_batches": 1e-07 }, - "vertex_ai/imagegeneration@006": { - "deprecation_date": "2025-09-24", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-002": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-capability-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" - }, - "vertex_ai/imagen-4.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-ultra-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, "vertex_ai/jamba-1.5": { "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", @@ -53251,51 +48182,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "vertex_ai/veo-2.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.35, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.4, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, @@ -53584,59 +48470,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/zai-org/GLM-4.5": { - "deprecation_date": "2026-03-04", - "supports_reasoning": true, - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.2, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "deprecation_date": "2026-08-04", - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "deprecation_date": "2026-08-25", - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" - }, - "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "deprecation_date": "2026-08-04", - "supports_reasoning": true, - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/moonshotai/Kimi-K2-Instruct": { - "deprecation_date": "2026-03-04", - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/moonshotai/Kimi-K2.5": { "max_tokens": 262144, "max_input_tokens": 262144, @@ -53652,20 +48485,6 @@ "supports_response_schema": true, "supports_vision": true }, - "wandb/MiniMaxAI/MiniMax-M2.5": { - "deprecation_date": "2026-08-25", - "max_tokens": 197000, - "max_input_tokens": 197000, - "max_output_tokens": 197000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true - }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_tokens": 128000, "max_input_tokens": 131000, @@ -53687,27 +48506,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/deepseek-ai/DeepSeek-R1-0528": { - "deprecation_date": "2026-03-04", - "supports_reasoning": true, - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/deepseek-ai/DeepSeek-V3-0324": { - "deprecation_date": "2026-03-04", - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 1.14e-06, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 128000, "max_input_tokens": 128000, @@ -53718,26 +48516,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2026-04-21", - "max_tokens": 64000, - "max_input_tokens": 64000, - "max_output_tokens": 64000, - "input_cost_per_token": 1.7e-07, - "output_cost_per_token": 6.6e-07, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/microsoft/Phi-4-mini-instruct": { - "deprecation_date": "2026-08-04", - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.008, - "output_cost_per_token": 0.035, - "litellm_provider": "wandb", - "mode": "chat" - }, "watsonx/ibm/granite-3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "watsonx", @@ -54138,440 +48916,6 @@ "deprecation_date": "2027-02-26", "source": "https://developers.openai.com/api/docs/pricing" }, - "xai/grok-3": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-fast-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-fast-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini": { - "cache_read_input_token_cost": 2e-07, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-beta": { - "cache_read_input_token_cost": 2e-07, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-fast": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-fast-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-fast-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-fast-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-fast-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-0709": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-latest": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-reasoning-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-non-reasoning-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, "xai/grok-4.20-multi-agent-beta-0309": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, @@ -54816,72 +49160,6 @@ "supports_vision": true, "supports_web_search": true }, - "xai/grok-code-fast": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15", - "input_cost_per_image_token": 1e-06 - }, - "xai/grok-code-fast-1": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15", - "input_cost_per_image_token": 1e-06 - }, - "xai/grok-code-fast-1-0825": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15", - "input_cost_per_image_token": 1e-06 - }, "zai.glm-4.7": { "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", @@ -57624,30 +51902,6 @@ "supports_reasoning": true, "supports_vision": true }, - "scaleway/google/gemma-3-27b-it": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 40000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5e-07, - "supports_function_calling": true, - "supports_vision": true, - "deprecation_date": "2026-08-01" - }, - "scaleway/hcompany/holo2-30b-a3b": { - "input_cost_per_token": 3e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 22000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_reasoning": true, - "supports_vision": true, - "deprecation_date": "2026-08-09" - }, "scaleway/mistralai/mistral-medium-3.5-128b": { "input_cost_per_token": 1.5e-06, "litellm_provider": "scaleway", @@ -57661,29 +51915,6 @@ "supports_vision": true, "supports_tool_choice": true }, - "scaleway/mistralai/devstral-2-123b-instruct-2512": { - "input_cost_per_token": 4e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_function_calling": true, - "deprecation_date": "2026-08-01" - }, - "scaleway/mistralai/voxtral-small-24b-2507": { - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 32000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3.5e-07, - "supports_audio_input": true, - "deprecation_date": "2026-08-01" - }, "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": { "input_cost_per_token": 1.5e-07, "litellm_provider": "scaleway", @@ -59243,26 +53474,6 @@ "/v1/audio/speech" ] }, - "gpt-4o-mini-tts-2025-03-20": { - "deprecation_date": "2026-07-23", - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "mode": "audio_speech", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, - "output_cost_per_token": 1e-05, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/audio/speech" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ] - }, "gpt-4o-mini-tts-2025-12-15": { "input_cost_per_token": 6e-07, "litellm_provider": "openai", @@ -59366,41 +53577,6 @@ "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false }, - "gpt-realtime-mini-2025-10-06": { - "cache_creation_input_audio_token_cost": 3e-07, - "cache_read_input_audio_token_cost": 3e-07, - "cache_read_input_token_cost": 6e-08, - "deprecation_date": "2026-07-23", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_image_token": 8e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-realtime-mini-2025-12-15": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, @@ -59555,42 +53731,6 @@ "tpm": 250000, "rpm": 10 }, - "gemini/gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, @@ -65750,23 +59890,6 @@ "image" ] }, - "xai/grok-imagine-image-pro": { - "input_cost_per_image": 0.05, - "litellm_provider": "xai", - "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", - "supported_endpoints": [ - "/v1/images/generations" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "image" - ], - "deprecation_date": "2026-05-15" - }, "xai/grok-imagine-image-2.0": { "input_cost_per_image": 0.06, "litellm_provider": "xai", @@ -66384,16 +60507,6 @@ "output_cost_per_token": 2.82e-07, "source": "https://api.together.ai/v1/models" }, - "together_ai/moonshotai/Kimi-K2.6": { - "deprecation_date": "2026-08-19", - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4.5e-06, - "cache_read_input_token_cost": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.8e-06, @@ -66411,25 +60524,6 @@ "mode": "chat", "source": "https://api.together.ai/v1/models" }, - "together_ai/zai-org/GLM-5": { - "deprecation_date": "2026-06-22", - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, - "together_ai/zai-org/GLM-5.1": { - "deprecation_date": "2026-07-10", - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "together_ai/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, "output_cost_per_token": 7e-06, @@ -66438,33 +60532,6 @@ "mode": "chat", "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3-Coder-Next-FP8": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen3-VL-32B-Instruct": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen3-VL-8B-Instruct": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 6.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -66489,15 +60556,6 @@ "mode": "chat", "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/QwQ-32B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "cerebras/gemma-4-31b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", @@ -71240,37 +65298,14 @@ "output_cost_per_token": 1.5e-07, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { - "deprecation_date": "2024-08-22", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "mode": "chat", + "vertex_ai/gemini-2.5-flash-native-audio": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.6e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://api.together.ai/v1/models" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, @@ -71321,14 +65356,6 @@ "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "together_ai/google/gemma-2-27b-it": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, "gpt-5.5-cyber": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 1.25e-05, @@ -71346,14 +65373,6 @@ "output_cost_per_token": 2.5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, - "together_ai/meta-llama/Llama-3-8b-chat-hf": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/meta-llama/Llama-3.1-405B-Instruct": { "input_cost_per_token": 3.5e-06, "litellm_provider": "together_ai", @@ -71375,38 +65394,6 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models" }, - "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", @@ -71414,22 +65401,6 @@ "output_cost_per_token": 2e-08, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen2-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 9e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen2-VL-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", @@ -71444,22 +65415,6 @@ "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { - "deprecation_date": "2026-01-05", - "input_cost_per_token": 1.95e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://api.together.ai/v1/models" - }, "azure/eu/codex-mini": { "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, @@ -71610,15 +65565,6 @@ "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/gpt-5.2-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/eu/gpt-5.2-codex": { "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, @@ -71637,15 +65583,6 @@ "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/gpt-5.3-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/eu/gpt-5.3-codex": { "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, @@ -71964,15 +65901,6 @@ "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.2-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/us/gpt-5.2-codex": { "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, @@ -71991,15 +65919,6 @@ "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.3-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/us/gpt-5.3-codex": { "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 431e965524e..b48bdd6322c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -53,13 +53,6 @@ "mode": "image_generation", "output_cost_per_image": 0.04 }, - "1024-x-1024/dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 1.9e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -67,13 +60,6 @@ "mode": "image_generation", "output_cost_per_image": 0.08 }, - "256-x-256/dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 2.4414e-07, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -81,13 +67,6 @@ "mode": "image_generation", "output_cost_per_image": 0.018 }, - "512-x-512/dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 6.86e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -961,23 +940,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -993,23 +955,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", @@ -2971,60 +2916,6 @@ "supports_vision": true, "supports_tool_choice": true }, - "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, - "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, @@ -3052,23 +2943,6 @@ "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06 }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -3446,29 +3320,6 @@ "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024 }, - "azure_ai/claude-opus-4-1": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "azure_ai/claude-sonnet-4-5": { "deprecation_date": "2026-10-19", "cache_creation_input_token_cost": 3.75e-06, @@ -4503,43 +4354,6 @@ "output_cost_per_token_priority": 2.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.375e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.375e-07, @@ -4832,43 +4646,6 @@ "output_cost_per_token_priority": 2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/global/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, @@ -4944,19 +4721,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-3.5-turbo-0125": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-3.5-turbo-instruct-0914": { "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_text", @@ -4976,32 +4740,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-35-turbo-0125": { - "deprecation_date": "2025-05-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-1106": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 1e-06, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-35-turbo-16k": { "input_cost_per_token": 3e-06, "litellm_provider": "azure", @@ -5769,40 +5507,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/gpt-realtime-2": { - "cache_read_input_audio_token_cost": 4e-07, - "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2026-08-31", - "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image_token": 5e-06, - "input_cost_per_token": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 6.4e-05, - "output_cost_per_token": 2.4e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, @@ -6100,45 +5804,6 @@ "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 }, - "azure/gpt-5.1-chat-2025-11-13": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, @@ -6289,73 +5954,6 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 6.25e-08 }, - "azure/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-03-17", @@ -6617,43 +6215,6 @@ "output_cost_per_token_priority": 2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, @@ -6832,78 +6393,6 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 8.75e-08 }, - "azure/gpt-5.2-chat": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5.2-chat-2025-12-11": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-05-13", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2027-07-13", @@ -6936,42 +6425,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5.3-chat": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, @@ -10563,43 +10016,6 @@ "output_cost_per_token_priority": 2.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.375e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.375e-07, @@ -11201,18 +10617,6 @@ "/v1/images/edits" ] }, - "azure_ai/MAI-Image-2e": { - "deprecation_date": "2026-08-15", - "input_cost_per_token": 5e-06, - "litellm_provider": "azure_ai", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "output_cost_per_image_token": 1.95e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, "azure_ai/MAI-Thinking-1": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, @@ -11237,34 +10641,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.7e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 2.04e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.04e-06, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure_ai/Llama-3.3-70B-Instruct": { "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", @@ -11313,18 +10689,6 @@ "output_cost_per_token": 3.7e-07, "supports_tool_choice": true }, - "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 5.33e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 1.6e-05, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, "azure_ai/Meta-Llama-3.1-70B-Instruct": { "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", @@ -11336,18 +10700,6 @@ "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.1e-07, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, "azure_ai/Phi-3-medium-128k-instruct": { "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", @@ -11518,16 +10870,6 @@ "supports_tool_choice": true, "supports_reasoning": true }, - "azure_ai/mistral-document-ai-2505": { - "deprecation_date": "2026-07-20", - "litellm_provider": "azure_ai", - "ocr_cost_per_page": 0.003, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr" - ], - "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" - }, "azure_ai/mistral-document-ai-2512": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, @@ -11628,17 +10970,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "azure_ai/cohere-rerank-v3.5": { - "deprecation_date": "2026-05-14", - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 - }, "azure_ai/cohere-rerank-v4.0-pro": { "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, @@ -11691,19 +11022,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/deepseek-r1": { - "deprecation_date": "2026-08-13", - "input_cost_per_token": 1.35e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_reasoning": true, - "supports_tool_choice": true - }, "azure_ai/deepseek-v3": { "input_cost_per_token": 1.14e-06, "litellm_provider": "azure_ai", @@ -11715,33 +11033,6 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, - "azure_ai/deepseek-v3-0324": { - "deprecation_date": "2026-07-13", - "input_cost_per_token": 1.14e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/deepseek-v3.1": { - "deprecation_date": "2026-07-13", - "input_cost_per_token": 1.23e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.94e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "azure_ai/deepseek-v4-pro": { "deprecation_date": "2028-02-20", "input_cost_per_token": 1.74e-06, @@ -11808,68 +11099,6 @@ ], "supports_embedding_image_input": true }, - "azure_ai/global/grok-3": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/global/grok-3-mini": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3-mini": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", @@ -11963,36 +11192,6 @@ "supports_vision": true, "supports_web_search": true }, - "azure_ai/grok-4-fast-non-reasoning": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-4-fast-reasoning": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/grok-4-1-fast-non-reasoning": { "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, @@ -13516,40 +12715,6 @@ "mode": "chat", "output_cost_per_token": 1.5e-06 }, - "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-07, - "cache_creation_input_token_cost": 4.5e-06 - }, - "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, @@ -13727,61 +12892,6 @@ "mode": "chat", "output_cost_per_token": 1.5e-06 }, - "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 4.5e-06, - "cache_read_input_token_cost": 3.6e-07, - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-07, - "cache_creation_input_token_cost": 4.5e-06 - }, - "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, @@ -14219,34 +13329,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "cerebras/zai-glm-4.6": { - "deprecation_date": "2026-01-20", - "input_cost_per_token": 2.25e-06, - "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-06, - "source": "https://www.cerebras.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "cerebras/zai-glm-4.7": { - "deprecation_date": "2026-08-17", - "input_cost_per_token": 2.25e-06, - "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-06, - "source": "https://www.cerebras.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "cerebras/qwen-3.8-27b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", @@ -14272,23 +13354,6 @@ "mode": "chat", "output_cost_per_token": 5e-07 }, - "chatgpt-4o-latest": { - "deprecation_date": "2026-02-17", - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-transcribe-diarize": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -14351,131 +13416,6 @@ "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-3-7-sonnet-20250219": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-02-19", - "input_cost_per_token": 3e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "claude-3-haiku-20240307": { - "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 5e-07, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-04-20", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-3-opus-20240229": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "deprecation_date": "2026-01-05", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-4-opus-20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "deprecation_date": "2026-06-15", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-4-sonnet-20250514": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "deprecation_date": "2026-06-15", - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "prompt_cache_min_tokens": 1024 - }, "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -14654,92 +13594,6 @@ "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06 }, - "claude-opus-4-1": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "deprecation_date": "2026-08-05" - }, - "claude-opus-4-1-20250805": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "deprecation_date": "2026-08-05", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-opus-4-20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "deprecation_date": "2026-06-15", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15167,38 +14021,6 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-sonnet-4-20250514": { - "deprecation_date": "2026-06-15", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", @@ -15551,36 +14373,6 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "codex-mini-latest": { - "cache_read_input_token_cost": 3.75e-07, - "deprecation_date": "2026-02-12", - "input_cost_per_token": 1.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 6e-06, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "cohere.command-light-text-v14": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", @@ -15680,16 +14472,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "command": { - "input_cost_per_token": 1e-06, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "completion", - "output_cost_per_token": 2e-06, - "deprecation_date": "2025-09-15" - }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", @@ -15716,17 +14498,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "command-light": { - "input_cost_per_token": 3e-07, - "litellm_provider": "cohere_chat", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-nightly": { "input_cost_per_token": 1e-06, "litellm_provider": "cohere", @@ -15736,18 +14507,6 @@ "mode": "completion", "output_cost_per_token": 2e-06 }, - "command-r": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_function_calling": true, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-r-08-2024": { "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", @@ -15759,18 +14518,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "command-r-plus": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-r-plus-08-2024": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", @@ -15823,26 +14570,6 @@ "supports_vision": true, "source": "https://platform.openai.com/docs/models/computer-use-preview" }, - "dall-e-2": { - "deprecation_date": "2026-05-12", - "input_cost_per_image": 0.02, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations", - "/v1/images/edits", - "/v1/images/variations" - ] - }, - "dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_image": 0.04, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 2.8e-07, @@ -18839,30 +17566,6 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, - "databricks/databricks-claude-3-7-sonnet": { - "cache_creation_input_token_cost": 3.74997e-06, - "cache_read_input_token_cost": 3.0002e-07, - "deprecation_date": "2026-04-12", - "input_cost_per_token": 2.9999900000000002e-06, - "input_dbu_cost_per_token": 4.2857e-05, - "litellm_provider": "databricks", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_anthropic_thinking_payload": true, - "supports_tool_choice": true - }, "databricks/databricks-claude-fable-5": { "cache_creation_input_token_cost": 1.250004e-05, "cache_read_input_token_cost": 1.00002e-06, @@ -19825,44 +18528,6 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, - "databricks/databricks-gpt-5-1-codex-max": { - "cache_creation_input_token_cost": 1.24999e-06, - "cache_read_input_token_cost": 1.2502e-07, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 1.24999e-06, - "input_dbu_cost_per_token": 1.7857e-05, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, - "output_dbu_cost_per_token": 0.000142857, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, - "databricks/databricks-gpt-5-1-codex-mini": { - "cache_creation_input_token_cost": 2.4997e-07, - "cache_read_input_token_cost": 2.499e-08, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 2.4997e-07, - "input_dbu_cost_per_token": 3.571e-06, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.99997e-06, - "output_dbu_cost_per_token": 2.8571e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, "databricks/databricks-gpt-5-2": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, @@ -19883,25 +18548,6 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, - "databricks/databricks-gpt-5-2-codex": { - "cache_creation_input_token_cost": 1.75e-06, - "cache_read_input_token_cost": 1.75e-07, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 1.75e-06, - "input_dbu_cost_per_token": 2.5e-05, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_dbu_cost_per_token": 0.0002, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, "databricks/databricks-gpt-5-3-codex": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, @@ -20328,25 +18974,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "databricks/databricks-llama-2-70b-chat": { - "cache_creation_input_token_cost": 5.0001e-07, - "cache_read_input_token_cost": 5.0001e-07, - "deprecation_date": "2024-10-30", - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, - "output_dbu_cost_per_token": 2.1429e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-llama-4-maverick": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, @@ -20365,25 +18992,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-1-405b-instruct": { - "cache_creation_input_token_cost": 5.00003e-06, - "cache_read_input_token_cost": 5.00003e-06, - "deprecation_date": "2026-02-15", - "input_cost_per_token": 5.00003e-06, - "input_dbu_cost_per_token": 7.1429e-05, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, @@ -20419,82 +19027,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-70b-instruct": { - "cache_creation_input_token_cost": 1.00002e-06, - "cache_read_input_token_cost": 1.00002e-06, - "deprecation_date": "2024-07-23", - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 2.9999900000000002e-06, - "output_dbu_cost_per_token": 4.2857e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mixtral-8x7b-instruct": { - "cache_creation_input_token_cost": 5.0001e-07, - "cache_read_input_token_cost": 5.0001e-07, - "deprecation_date": "2025-04-30", - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.00002e-06, - "output_dbu_cost_per_token": 1.4286e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-30b-instruct": { - "cache_creation_input_token_cost": 1.00002e-06, - "cache_read_input_token_cost": 1.00002e-06, - "deprecation_date": "2024-08-30", - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.00002e-06, - "output_dbu_cost_per_token": 1.4286e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-7b-instruct": { - "cache_creation_input_token_cost": 5.0001e-07, - "cache_read_input_token_cost": 5.0001e-07, - "deprecation_date": "2024-08-30", - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-qwen35-122b-a10b": { "cache_creation_input_token_cost": 2.2001e-07, "cache_read_input_token_cost": 2.2001e-07, @@ -21559,18 +20091,6 @@ "supports_tool_choice": true, "supports_function_calling": true }, - "deepinfra/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_function_calling": true - }, "deepinfra/google/gemini-2.5-flash": { "max_tokens": 1000000, "max_input_tokens": 1000000, @@ -22429,15 +20949,6 @@ "/v1/audio/speech" ] }, - "embed-english-light-v2.0": { - "deprecation_date": "2026-04-04", - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", @@ -22446,15 +20957,6 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, - "embed-english-v2.0": { - "deprecation_date": "2026-04-04", - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_tokens": 4096, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-english-v3.0": { "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, @@ -22469,15 +20971,6 @@ "supports_embedding_image_input": true, "supports_image_input": true }, - "embed-multilingual-v2.0": { - "deprecation_date": "2026-04-04", - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 768, - "max_tokens": 768, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", @@ -22645,23 +21138,6 @@ "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -22677,23 +21153,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, @@ -25265,26 +23724,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { - "cache_read_input_token_cost": 6e-07, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 1.2e-06, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "cache_read_input_token_cost_priority": 5.5e-08, @@ -25672,26 +24111,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { - "cache_read_input_token_cost": 6e-08, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 3e-07, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, @@ -25779,26 +24198,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/deepseek-v4-pro": { - "cache_read_input_token_cost": 6e-07, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 1.2e-06, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, @@ -25998,26 +24397,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/minimax-m2p7": { - "cache_read_input_token_cost": 6e-08, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 3e-07, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, @@ -26195,31 +24574,6 @@ "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B": { - "litellm_provider": "friendliai", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 1.2e-07, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "Frontier-scale multilingual language model developed by LG AI Research", - "deprecation_date": "2026-09-06", - "source": "https://api.friendli.ai/serverless/v1/models" - }, "friendliai/deepseek-ai/DeepSeek-V3.2": { "litellm_provider": "friendliai", "max_input_tokens": 163840, @@ -26525,160 +24879,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_character": 3.75e-08, - "input_cost_per_token": 1.5e-07, - "input_cost_per_token_batches": 7.5e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_batches": 3e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-001": { - "cache_read_input_token_cost": 3.75e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_audio_token_batches": 3.75e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_batches": 3.75e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "output_cost_per_token_batches": 1.5e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, "deprecation_date": "2026-10-20", @@ -27503,53 +25703,6 @@ }, "gemini_native_audio": true }, - "gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, "gemini-2.5-pro": { "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1.25e-07, @@ -27608,62 +25761,6 @@ "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05 }, - "gemini-3-pro-preview": { - "deprecation_date": "2026-03-26", - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, @@ -28322,51 +26419,6 @@ "supports_url_context": true, "supports_vision": true }, - "gemini/gemini-robotics-er-1.5-preview": { - "cache_read_input_token_cost": 0, - "deprecation_date": "2026-04-30", - "input_cost_per_token": 3e-07, - "input_cost_per_audio_token": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "video", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "rpm": 10, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini/gemini-robotics-er-2-preview": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, @@ -28417,53 +26469,6 @@ "supports_web_search": true, "web_search_billing_unit": "per_query" }, - "gemini/gemini-robotics-er-1.6-preview": { - "deprecation_date": "2026-08-31", - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 5e-06, - "output_cost_per_token": 5e-06, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "web_search_billing_unit": "per_query" - }, "gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, @@ -28600,27 +26605,6 @@ "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", "tpm": 10000000 }, - "gemini/gemini-embedding-2-preview": { - "deprecation_date": "2026-08-10", - "input_cost_per_audio_token": 6.5e-06, - "input_cost_per_audio_token_batches": 3.25e-06, - "input_cost_per_image_token": 4.5e-07, - "input_cost_per_image_token_batches": 2.25e-07, - "input_cost_per_token": 2e-07, - "input_cost_per_token_batches": 1e-07, - "input_cost_per_video_token": 1.2e-05, - "input_cost_per_video_token_batches": 6e-06, - "litellm_provider": "gemini", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supports_multimodal": true, - "tpm": 10000000 - }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, @@ -28643,135 +26627,6 @@ "supports_vision": true, "tpm": 10000000 }, - "gemini/gemini-1.5-flash": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", - "supports_multimodal": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-001": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini/gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 3e-08, @@ -28934,50 +26789,6 @@ "web_search_billing_unit": "per_query", "supports_reasoning": false }, - "gemini/gemini-3-pro-image-preview": { - "deprecation_date": "2026-06-25", - "input_cost_per_image": 0.0011, - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, - "output_cost_per_token": 1.2e-05, - "rpm": 1000, - "tpm": 4000000, - "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -29063,49 +26874,6 @@ }, "web_search_billing_unit": "per_query" }, - "gemini/gemini-3.1-flash-image-preview": { - "deprecation_date": "2026-06-25", - "input_cost_per_token": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.045, - "output_cost_per_image_token": 6e-05, - "output_cost_per_token": 3e-06, - "output_cost_per_token_batches": 1.5e-06, - "rpm": 1000, - "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, @@ -29244,104 +27012,6 @@ "supports_audio_input": true, "supports_image_size": false }, - "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 1e-08, - "deprecation_date": "2026-03-31", - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-02-17", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, @@ -29459,55 +27129,6 @@ "supports_video_input": true, "web_search_billing_unit": "per_query" }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, "gemini/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, @@ -29618,114 +27239,6 @@ "supports_vision": true, "tpm": 800000 }, - "gemini/gemini-3-pro-preview": { - "deprecation_date": "2026-03-09", - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-05-25", - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 - }, "gemini/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, @@ -30826,34 +28339,6 @@ "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "gemini/imagen-3.0-generate-002": { - "deprecation_date": "2025-11-10", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-fast-generate-001": { - "deprecation_date": "2026-08-17", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-generate-001": { - "deprecation_date": "2026-08-17", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-ultra-generate-001": { - "deprecation_date": "2026-08-17", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, "gemini/learnlm-1.5-pro-experimental": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -30932,21 +28417,6 @@ "supports_web_search": false, "output_cost_per_image": 0.08 }, - "gemini/veo-2.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "gemini", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.35, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, "gemini/veo-3.1-fast-generate-preview": { "litellm_provider": "gemini", "max_input_tokens": 1024, @@ -32156,33 +29626,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-0125-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 3e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0314": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 3e-05, - "litellm_provider": "openai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4-0613": { "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-05, @@ -32252,22 +29695,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-turbo-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 3e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4.1": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, @@ -32610,24 +30037,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-audio-preview": { - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 4e-05, @@ -32812,44 +30221,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "gpt-audio-mini-2025-10-06": { - "deprecation_date": "2026-07-23", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, "gpt-audio-mini-2025-12-15": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, @@ -32946,24 +30317,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-mini-audio-preview": { - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 6e-07, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1e-05, @@ -32982,26 +30335,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4o-mini-realtime-preview": { - "cache_creation_input_audio_token_cost": 3e-07, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, @@ -33048,32 +30381,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-mini-search-preview-2025-03-11": { - "cache_read_input_token_cost": 7.5e-08, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.5e-07, - "input_cost_per_token_batches": 7.5e-08, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_batches": 3e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.025, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.025 - }, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -33108,63 +30415,6 @@ "audio" ] }, - "gpt-4o-realtime-preview": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2025-06-03": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -33191,32 +30441,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-search-preview-2025-03-11": { - "cache_read_input_token_cost": 1.25e-06, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_batches": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_batches": 5e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.025, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.025 - }, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -33879,52 +31103,6 @@ "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false }, - "gpt-5.1-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, @@ -34031,94 +31209,6 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, - "gpt-5.2-chat-latest": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-08-10", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.3-chat-latest": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-08-10", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, "gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, "input_cost_per_token_batches": 1.05e-05, @@ -35783,251 +32873,6 @@ "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, - "gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex-mini": { - "cache_read_input_token_cost": 2.5e-08, - "cache_read_input_token_cost_priority": 4.5e-08, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_priority": 4.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 2e-06, - "output_cost_per_token_priority": 3.6e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, "gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, @@ -36870,32 +33715,6 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/llama-3.1-8b-instant": { - "deprecation_date": "2026-08-16", - "input_cost_per_token": 5e-08, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-versatile": { - "deprecation_date": "2026-08-16", - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/llama-guard-3-8b": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", @@ -36905,19 +33724,6 @@ "output_cost_per_token": 2e-07, "source": "https://console.groq.com/docs/model/llama-guard-3-8b" }, - "groq/gemma-7b-it": { - "deprecation_date": "2024-12-18", - "input_cost_per_token": 5e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/meta-llama/llama-prompt-guard-2-22m": { "input_cost_per_token": 3e-08, "litellm_provider": "groq", @@ -36938,58 +33744,6 @@ "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" }, - "groq/meta-llama/llama-guard-4-12b": { - "deprecation_date": "2026-03-05", - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07 - }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "deprecation_date": "2026-03-09", - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "deprecation_date": "2026-07-17", - "input_cost_per_token": 1.1e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3.4e-07, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/moonshotai/kimi-k2-instruct-0905": { - "deprecation_date": "2026-04-15", - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "groq", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "groq/openai/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, @@ -37070,45 +33824,6 @@ "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, - "groq/playai-tts": { - "deprecation_date": "2025-12-31", - "input_cost_per_character": 5e-05, - "litellm_provider": "groq", - "max_input_tokens": 10000, - "max_output_tokens": 10000, - "max_tokens": 10000, - "mode": "audio_speech" - }, - "groq/qwen/qwen3.6-27b": { - "input_cost_per_token": 6e-07, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://console.groq.com/docs/model/qwen/qwen3.6-27b", - "deprecation_date": "2026-09-14", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/qwen/qwen3-32b": { - "deprecation_date": "2026-07-17", - "input_cost_per_token": 2.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 5.9e-07, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/whisper-large-v3": { "input_cost_per_second": 3.083e-05, "litellm_provider": "groq", @@ -37121,27 +33836,6 @@ "mode": "audio_transcription", "output_cost_per_second": 0.0 }, - "hd/1024-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 7.629e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "hd/1024-x-1792/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 6.539e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "hd/1792-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 6.539e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", "max_tokens": 8192, @@ -38968,19 +35662,6 @@ "supports_system_messages": true, "supports_native_structured_output": true }, - "mistral/codestral-2405": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 1e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 3e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/codestral-2508": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, @@ -39024,51 +35705,6 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "mistral/devstral-medium-2507": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2505": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2507": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-small-latest": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, @@ -39084,21 +35720,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/labs-devstral-small-2512": { - "deprecation_date": "2026-03-31", - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-latest": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, @@ -39129,21 +35750,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/devstral-2512": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/ministral-14b-2512": { "input_cost_per_token": 2e-07, "litellm_provider": "mistral", @@ -39419,54 +36025,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/magistral-medium-2506": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-medium-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-medium-1-2-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-ocr-latest": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, @@ -39506,20 +36064,6 @@ "/v1/batch" ] }, - "mistral/mistral-ocr-2505-completion": { - "deprecation_date": "2026-05-31", - "litellm_provider": "mistral", - "ocr_cost_per_page": 0.001, - "ocr_cost_per_page_batches": 0.0005, - "annotation_cost_per_page": 0.003, - "annotation_cost_per_page_batches": 0.0015, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr", - "/v1/batch" - ], - "source": "https://mistral.ai/pricing#api-pricing" - }, "mistral/mistral-ocr-2512": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.002, @@ -39550,22 +36094,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/magistral-small-2506": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/magistral-small-latest": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, @@ -39583,22 +36111,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/magistral-small-1-2-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-embed": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", @@ -39622,48 +36134,6 @@ "max_tokens": 8192, "mode": "embedding" }, - "mistral/mistral-large-2402": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 4e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2407": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2411": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-large-latest": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, @@ -39733,49 +36203,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-2312": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 2.7e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 8.1e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2505": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2508": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-2604": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, @@ -39818,22 +36245,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-3-1-2508": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-3-5": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, @@ -39890,22 +36301,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-small-3-2-2506": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 6e-08, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/ministral-3-3b-2512": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, @@ -39999,32 +36394,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/open-codestral-mamba": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-7b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/open-mistral-nemo": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, @@ -40039,78 +36408,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/open-mistral-nemo-2407": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x22b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x7b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 7e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/pixtral-12b-2409": { - "deprecation_date": "2025-12-31", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/pixtral-large-2411": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/pixtral-large-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, @@ -40159,36 +36456,6 @@ "supports_audio_input": false, "supports_response_schema": true }, - "moonshot/kimi-k2-0711-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-0905-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "moonshot/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, @@ -40207,21 +36474,6 @@ "supports_video_input": true, "supports_vision": true }, - "moonshot/kimi-k2-turbo-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 1.15e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, @@ -40278,111 +36530,6 @@ "supports_video_input": true, "supports_vision": true }, - "moonshot/kimi-latest": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-128k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-32k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-8k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-thinking-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2025-11-11", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_vision": true - }, - "moonshot/kimi-k2-thinking": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-thinking-turbo": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 1.15e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "moonshot/moonshot-v1-128k": { "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -40396,19 +36543,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-128k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-128k-vision-preview": { "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -40436,19 +36570,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-32k-vision-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", @@ -40476,19 +36597,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-8k-vision-preview": { "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", @@ -41679,88 +37787,6 @@ "supports_vision": true, "supports_web_search": true }, - "o3-deep-research": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1e-05, - "input_cost_per_token_batches": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "output_cost_per_token_batches": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o3-deep-research-2025-06-26": { - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1e-05, - "input_cost_per_token_batches": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "output_cost_per_token_batches": 2e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "o3-mini": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-10-23", @@ -41946,88 +37972,6 @@ "supports_vision": true, "supports_web_search": true }, - "o4-mini-deep-research": { - "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o4-mini-deep-research-2025-06-26": { - "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "oci/meta.llama-3.1-8b-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", @@ -43509,23 +39453,6 @@ "supports_vision": false, "supports_web_search": false }, - "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "openrouter/google/gemini-2.5-flash": { "cache_creation_input_token_cost": 8.33333333333333e-08, "cache_read_input_audio_token_cost": 1e-07, @@ -46699,17 +42626,6 @@ "supports_reasoning": true, "supports_system_messages": true }, - "rerank-english-v2.0": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0, - "deprecation_date": "2025-04-30" - }, "rerank-english-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, @@ -46720,17 +42636,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "rerank-multilingual-v2.0": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0, - "deprecation_date": "2025-04-30" - }, "rerank-multilingual-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, @@ -46871,31 +42776,6 @@ "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2026-03-20", - "input_cost_per_token": 7e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 3e-06, - "litellm_provider": "sambanova", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/Llama-4-Maverick-17B-128E-Instruct": { "input_cost_per_token": 6.3e-07, "litellm_provider": "sambanova", @@ -46913,73 +42793,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 4e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - }, - "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-06, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 1e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 4e-08, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-08, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 8e-08, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.6e-07, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, "sambanova/Meta-Llama-3.3-70B-Instruct": { "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", @@ -46993,54 +42806,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "sambanova/Meta-Llama-Guard-3-8B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 3e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/QwQ-32B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 5e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_audio_input": true - }, - "sambanova/Qwen3-32B": { - "deprecation_date": "2026-04-06", - "input_cost_per_token": 4e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/DeepSeek-V3.1": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -47633,27 +43398,6 @@ "mode": "image_generation", "output_cost_per_image": 0.14 }, - "standard/1024-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 3.81469e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "standard/1024-x-1792/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 4.359e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "standard/1792-x-1024/dall-e-3": { - "deprecation_date": "2026-05-12", - "input_cost_per_pixel": 4.359e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "linkup/search": { "input_cost_per_query": 0.00587, "litellm_provider": "linkup", @@ -47788,36 +43532,6 @@ "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "text-moderation-007": { - "deprecation_date": "2025-10-27", - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "text-moderation-latest": { - "deprecation_date": "2025-10-27", - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "text-moderation-stable": { - "deprecation_date": "2025-10-27", - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, "text-multilingual-embedding-002": { "deprecation_date": "2027-04-01", "input_cost_per_character": 2.5e-08, @@ -47915,19 +43629,6 @@ "mode": "chat", "output_cost_per_token": 1e-07 }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "max_input_tokens": 131072, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", "mode": "chat", @@ -47940,87 +43641,6 @@ "max_input_tokens": 32768, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "deprecation_date": "2026-07-10", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_tool_choice": false - }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "deprecation_date": "2026-06-04", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 3e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, - "metadata": { - "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" - }, - "mode": "chat", - "output_cost_per_token": 7e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "deprecation_date": "2026-02-03", - "input_cost_per_token": 5.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.19e-06, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", @@ -48037,33 +43657,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_tokens": 16384, - "metadata": { - "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" - }, - "mode": "chat", - "output_cost_per_token": 1.7e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "max_input_tokens": 131072, - "max_output_tokens": 16384 - }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", @@ -48077,112 +43670,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 0, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "deprecation_date": "2026-03-31", - "input_cost_per_token": 2.7e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.5e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 5.9e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 3.5e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 3.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "deprecation_date": "2025-11-13", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "max_input_tokens": 32768, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "deprecation_date": "2026-04-02", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_input_tokens": 32768, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/moonshotai/Kimi-K2-Instruct": { "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", @@ -48211,19 +43698,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 5e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/togethercomputer/CodeLlama-34b-Instruct": { "litellm_provider": "together_ai", "mode": "chat", @@ -48231,19 +43705,6 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.1e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", @@ -48260,102 +43721,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.7": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 4.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "max_tokens": 202752, - "metadata": { - "successor": "together_ai/zai-org/GLM-5.2" - }, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "together_ai/moonshotai/Kimi-K2.5": { - "deprecation_date": "2026-05-21", - "input_cost_per_token": 5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "max_tokens": 256000, - "metadata": { - "successor": "together_ai/moonshotai/Kimi-K3" - }, - "mode": "chat", - "output_cost_per_token": 2.8e-06, - "source": "https://www.together.ai/models/kimi-k2-5", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_reasoning": true - }, - "together_ai/moonshotai/Kimi-K2-Instruct-0905": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 1e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/moonshotai/Kimi-K3" - }, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://www.together.ai/models/kimi-k2-0905", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/Qwen/Qwen3.7-Plus" - }, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/Qwen/Qwen3.6-Plus" - }, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3.5-397B-A17B": { - "cache_read_input_token_cost": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, @@ -48477,23 +43842,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V4-Pro": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.74e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 512000, - "max_tokens": 512000, - "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, "deprecation_date": "2026-09-29", @@ -48510,52 +43858,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/google/gemma-3n-E4B-it": { - "deprecation_date": "2026-08-25", - "input_cost_per_token": 6e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.2e-07, - "source": "https://docs.together.ai/docs/serverless-models" - }, - "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 3.9e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 9.7e-07, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 2e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 514, - "max_tokens": 514, - "mode": "embedding", - "output_cost_per_token": 2e-08, - "output_vector_size": 1024, - "source": "https://docs.together.ai/docs/serverless-models" - }, - "together_ai/meta-llama/Llama-Guard-4-12B": { - "deprecation_date": "2026-08-25", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.together.ai/docs/serverless-models" - }, "together_ai/meta-models/Muse-Glimmer-30B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, @@ -48567,23 +43869,6 @@ "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, - "together_ai/moonshotai/Kimi-K2.7-Code": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 1.9e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -48606,33 +43891,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 512288, - "max_tokens": 512288, - "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://api.together.ai/v1/models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/pearl-ai/gemma-4-31b-it": { - "deprecation_date": "2026-08-27", - "input_cost_per_token": 2.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8.6e-07, - "source": "https://docs.together.ai/docs/serverless-models" - }, "together_ai/thinkingmachines/Inkling": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, @@ -48648,18 +43906,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-14", - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 524288, - "max_tokens": 524288, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models", - "supports_prompt_caching": true - }, "together_ai/zai-org/GLM-5.2": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, @@ -48923,23 +44169,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -48955,23 +44184,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, @@ -49036,23 +44248,6 @@ "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06 }, - "us-gov.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, @@ -50180,34 +45375,6 @@ "output_cost_per_token": 9e-07, "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, "vercel_ai_gateway/google/gemini-2.5-flash": { "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", @@ -51091,28 +46258,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-11", - "input_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-3-haiku": { "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", @@ -51191,72 +46336,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-opus-4": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-opus-4-1": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "output_cost_per_token_batches": 3.75e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "vertex_ai/claude-opus-4-1@20250805": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "output_cost_per_token_batches": 3.75e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, @@ -51857,98 +46936,6 @@ "supports_native_streaming": true, "prompt_cache_min_tokens": 1024 }, - "vertex_ai/claude-opus-4@20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-sonnet-4": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-sonnet-4@20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", @@ -52451,62 +47438,6 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "cache_read_input_token_cost_batches": 1e-07 }, - "vertex_ai/imagegeneration@006": { - "deprecation_date": "2025-09-24", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-002": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-capability-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" - }, - "vertex_ai/imagen-4.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-ultra-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, "vertex_ai/jamba-1.5": { "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", @@ -53251,51 +48182,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "vertex_ai/veo-2.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.35, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.4, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, @@ -53584,59 +48470,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/zai-org/GLM-4.5": { - "deprecation_date": "2026-03-04", - "supports_reasoning": true, - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.2, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "deprecation_date": "2026-08-04", - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "deprecation_date": "2026-08-25", - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" - }, - "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "deprecation_date": "2026-08-04", - "supports_reasoning": true, - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/moonshotai/Kimi-K2-Instruct": { - "deprecation_date": "2026-03-04", - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/moonshotai/Kimi-K2.5": { "max_tokens": 262144, "max_input_tokens": 262144, @@ -53652,20 +48485,6 @@ "supports_response_schema": true, "supports_vision": true }, - "wandb/MiniMaxAI/MiniMax-M2.5": { - "deprecation_date": "2026-08-25", - "max_tokens": 197000, - "max_input_tokens": 197000, - "max_output_tokens": 197000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true - }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_tokens": 128000, "max_input_tokens": 131000, @@ -53687,27 +48506,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/deepseek-ai/DeepSeek-R1-0528": { - "deprecation_date": "2026-03-04", - "supports_reasoning": true, - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/deepseek-ai/DeepSeek-V3-0324": { - "deprecation_date": "2026-03-04", - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 1.14e-06, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 128000, "max_input_tokens": 128000, @@ -53718,26 +48516,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2026-04-21", - "max_tokens": 64000, - "max_input_tokens": 64000, - "max_output_tokens": 64000, - "input_cost_per_token": 1.7e-07, - "output_cost_per_token": 6.6e-07, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/microsoft/Phi-4-mini-instruct": { - "deprecation_date": "2026-08-04", - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.008, - "output_cost_per_token": 0.035, - "litellm_provider": "wandb", - "mode": "chat" - }, "watsonx/ibm/granite-3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "watsonx", @@ -54138,440 +48916,6 @@ "deprecation_date": "2027-02-26", "source": "https://developers.openai.com/api/docs/pricing" }, - "xai/grok-3": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-fast-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-fast-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini": { - "cache_read_input_token_cost": 2e-07, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-beta": { - "cache_read_input_token_cost": 2e-07, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-fast": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-fast-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-fast-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-3-mini-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-fast-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-fast-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-0709": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-latest": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-reasoning-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, - "xai/grok-4-1-fast-non-reasoning-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07 - }, "xai/grok-4.20-multi-agent-beta-0309": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, @@ -54816,72 +49160,6 @@ "supports_vision": true, "supports_web_search": true }, - "xai/grok-code-fast": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15", - "input_cost_per_image_token": 1e-06 - }, - "xai/grok-code-fast-1": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15", - "input_cost_per_image_token": 1e-06 - }, - "xai/grok-code-fast-1-0825": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15", - "input_cost_per_image_token": 1e-06 - }, "zai.glm-4.7": { "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", @@ -57624,30 +51902,6 @@ "supports_reasoning": true, "supports_vision": true }, - "scaleway/google/gemma-3-27b-it": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 40000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5e-07, - "supports_function_calling": true, - "supports_vision": true, - "deprecation_date": "2026-08-01" - }, - "scaleway/hcompany/holo2-30b-a3b": { - "input_cost_per_token": 3e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 22000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_reasoning": true, - "supports_vision": true, - "deprecation_date": "2026-08-09" - }, "scaleway/mistralai/mistral-medium-3.5-128b": { "input_cost_per_token": 1.5e-06, "litellm_provider": "scaleway", @@ -57661,29 +51915,6 @@ "supports_vision": true, "supports_tool_choice": true }, - "scaleway/mistralai/devstral-2-123b-instruct-2512": { - "input_cost_per_token": 4e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_function_calling": true, - "deprecation_date": "2026-08-01" - }, - "scaleway/mistralai/voxtral-small-24b-2507": { - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 32000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3.5e-07, - "supports_audio_input": true, - "deprecation_date": "2026-08-01" - }, "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": { "input_cost_per_token": 1.5e-07, "litellm_provider": "scaleway", @@ -59243,26 +53474,6 @@ "/v1/audio/speech" ] }, - "gpt-4o-mini-tts-2025-03-20": { - "deprecation_date": "2026-07-23", - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "mode": "audio_speech", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, - "output_cost_per_token": 1e-05, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/audio/speech" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ] - }, "gpt-4o-mini-tts-2025-12-15": { "input_cost_per_token": 6e-07, "litellm_provider": "openai", @@ -59366,41 +53577,6 @@ "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false }, - "gpt-realtime-mini-2025-10-06": { - "cache_creation_input_audio_token_cost": 3e-07, - "cache_read_input_audio_token_cost": 3e-07, - "cache_read_input_token_cost": 6e-08, - "deprecation_date": "2026-07-23", - "input_cost_per_audio_token": 1e-05, - "input_cost_per_image_token": 8e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-realtime-mini-2025-12-15": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, @@ -59555,42 +53731,6 @@ "tpm": 250000, "rpm": 10 }, - "gemini/gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, @@ -65750,23 +59890,6 @@ "image" ] }, - "xai/grok-imagine-image-pro": { - "input_cost_per_image": 0.05, - "litellm_provider": "xai", - "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", - "supported_endpoints": [ - "/v1/images/generations" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "image" - ], - "deprecation_date": "2026-05-15" - }, "xai/grok-imagine-image-2.0": { "input_cost_per_image": 0.06, "litellm_provider": "xai", @@ -66384,16 +60507,6 @@ "output_cost_per_token": 2.82e-07, "source": "https://api.together.ai/v1/models" }, - "together_ai/moonshotai/Kimi-K2.6": { - "deprecation_date": "2026-08-19", - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4.5e-06, - "cache_read_input_token_cost": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.8e-06, @@ -66411,25 +60524,6 @@ "mode": "chat", "source": "https://api.together.ai/v1/models" }, - "together_ai/zai-org/GLM-5": { - "deprecation_date": "2026-06-22", - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, - "together_ai/zai-org/GLM-5.1": { - "deprecation_date": "2026-07-10", - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "together_ai/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, "output_cost_per_token": 7e-06, @@ -66438,33 +60532,6 @@ "mode": "chat", "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3-Coder-Next-FP8": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen3-VL-32B-Instruct": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen3-VL-8B-Instruct": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 6.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -66489,15 +60556,6 @@ "mode": "chat", "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/QwQ-32B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "source": "https://api.together.ai/v1/models" - }, "cerebras/gemma-4-31b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", @@ -71240,37 +65298,14 @@ "output_cost_per_token": 1.5e-07, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { - "deprecation_date": "2024-08-22", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "mode": "chat", + "vertex_ai/gemini-2.5-flash-native-audio": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.6e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://api.together.ai/v1/models" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, @@ -71321,14 +65356,6 @@ "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "together_ai/google/gemma-2-27b-it": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, "gpt-5.5-cyber": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 1.25e-05, @@ -71346,14 +65373,6 @@ "output_cost_per_token": 2.5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, - "together_ai/meta-llama/Llama-3-8b-chat-hf": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/meta-llama/Llama-3.1-405B-Instruct": { "input_cost_per_token": 3.5e-06, "litellm_provider": "together_ai", @@ -71375,38 +65394,6 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models" }, - "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", @@ -71414,22 +65401,6 @@ "output_cost_per_token": 2e-08, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen2-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 9e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen2-VL-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", @@ -71444,22 +65415,6 @@ "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { - "deprecation_date": "2026-01-05", - "input_cost_per_token": 1.95e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://api.together.ai/v1/models" - }, "azure/eu/codex-mini": { "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, @@ -71610,15 +65565,6 @@ "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/gpt-5.2-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/eu/gpt-5.2-codex": { "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, @@ -71637,15 +65583,6 @@ "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/gpt-5.3-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/eu/gpt-5.3-codex": { "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, @@ -71964,15 +65901,6 @@ "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.2-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/us/gpt-5.2-codex": { "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, @@ -71991,15 +65919,6 @@ "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.3-chat": { - "deprecation_date": "2026-06-29", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, "azure/us/gpt-5.3-codex": { "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, diff --git a/tests/test_litellm/integrations/test_anthropic_cache_control_hook.py b/tests/test_litellm/integrations/test_anthropic_cache_control_hook.py index 7bf4533979a..f787d370f04 100644 --- a/tests/test_litellm/integrations/test_anthropic_cache_control_hook.py +++ b/tests/test_litellm/integrations/test_anthropic_cache_control_hook.py @@ -1664,7 +1664,7 @@ class TestEnableAnthropicPromptCaching: points = self._points(model="us.anthropic.claude-sonnet-4-5-20250929-v1:0", provider="bedrock") assert [p["index"] for p in points] == [None, -1] - @pytest.mark.parametrize("model, provider", [("gpt-4o", "openai"), ("gemini-2.0-flash", "gemini")]) + @pytest.mark.parametrize("model, provider", [("gpt-4o", "openai")]) def test_non_anthropic_providers_never_injected(self, monkeypatch, model, provider): """These report supports_prompt_caching=True but never consume cache_control markers.""" from litellm.utils import supports_prompt_caching diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 5b21684ca9c..76ccdec25d0 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -299,42 +299,6 @@ def test_reasoning_tokens_gemini(_local_model_cost_map): ) -def test_reasoning_tokens_gemini_3_1_flash_lite(_local_model_cost_map): - """Test cost calculation for gemini-3.1-flash-lite-preview with reasoning tokens""" - model = "gemini-3.1-flash-lite-preview" - custom_llm_provider = "gemini" - - usage = Usage( - completion_tokens=1000, - prompt_tokens=500, - total_tokens=1500, - completion_tokens_details=CompletionTokensDetailsWrapper( - accepted_prediction_tokens=None, - audio_tokens=None, - reasoning_tokens=400, - rejected_prediction_tokens=None, - text_tokens=600, - ), - prompt_tokens_details=PromptTokensDetailsWrapper( - audio_tokens=None, cached_tokens=None, text_tokens=500, image_tokens=None - ), - ) - model_cost_map = litellm.model_cost[model] - prompt_cost, completion_cost = generic_cost_per_token( - model=model, - usage=usage, - custom_llm_provider=custom_llm_provider, - ) - - assert round(prompt_cost, 10) == round( - model_cost_map["input_cost_per_token"] * usage.prompt_tokens, - 10, - ) - assert round(completion_cost, 10) == round( - (model_cost_map["output_cost_per_token"] * usage.completion_tokens_details.text_tokens) - + (model_cost_map["output_cost_per_reasoning_token"] * usage.completion_tokens_details.reasoning_tokens), - 10, - ) def test_image_tokens_with_custom_pricing(): @@ -2221,65 +2185,8 @@ def test_vertex_image_generation_cost_falls_back_to_flat_image_pricing(_local_mo assert round(cost, 10) == round(expected_cost, 10) -def test_gemini_image_generation_cost_prefers_token_usage_metadata(_local_model_cost_map): - """ - When usage metadata exists on image responses, Gemini image generation cost - should be calculated from token pricing, not flat output_cost_per_image. - """ - - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - - input_text_tokens = 20 - input_image_tokens = 1120 - output_image_tokens = 1120 - prompt_tokens = input_text_tokens + input_image_tokens - - image_response = ImageResponse( - data=[ImageObject(b64_json="img1"), ImageObject(b64_json="img2")], - usage=ImageUsage( - input_tokens=prompt_tokens, - input_tokens_details=ImageUsageInputTokensDetails( - text_tokens=input_text_tokens, - image_tokens=input_image_tokens, - ), - output_tokens=output_image_tokens, - total_tokens=prompt_tokens + output_image_tokens, - ), - ) - - cost = gemini_image_generation_cost_calculator( - model=model, - image_response=image_response, - ) - - expected_prompt_cost = prompt_tokens * model_info["input_cost_per_token"] - expected_completion_cost = output_image_tokens * model_info["output_cost_per_image_token"] - expected_total_cost = expected_prompt_cost + expected_completion_cost - - assert round(cost, 10) == round(expected_total_cost, 10) - # Ensure this is not falling back to flat per-image pricing. - assert cost != len(image_response.data) * model_info["output_cost_per_image"] -def test_gemini_image_generation_cost_falls_back_to_flat_image_pricing(_local_model_cost_map): - """ - Without usage metadata, Gemini image generation cost should fall back to - output_cost_per_image * number_of_images. - """ - - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - - image_response = ImageResponse(data=[ImageObject(b64_json="img1"), ImageObject(b64_json="img2")]) - - cost = gemini_image_generation_cost_calculator( - model=model, - image_response=image_response, - ) - - expected_cost = len(image_response.data) * model_info["output_cost_per_image"] - assert round(cost, 10) == round(expected_cost, 10) def test_query_count_is_free_without_a_per_query_price(_local_model_cost_map): @@ -2460,23 +2367,6 @@ def test_vertex_global_or_absent_location_no_uplift(vertex_location, _local_mode assert base == located -@pytest.mark.parametrize("model", ["claude-opus-4-1", "gemini-2.0-flash-001"]) -def test_vertex_location_no_uplift_for_uniformly_priced_model(model, _local_model_cost_map): - """Models Google prices uniformly across endpoints (Gemini 2.x, Claude Opus 4.1 - and older) carry no multiplier and must not move with the location.""" - from litellm.types.utils import Usage - - usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500) - - base = generic_cost_per_token(model=model, usage=usage, custom_llm_provider="vertex_ai") - regional = generic_cost_per_token( - model=model, - usage=usage, - custom_llm_provider="vertex_ai", - vertex_location="us-east5", - ) - - assert base == regional, f"{model} should not have a regional-endpoint uplift" def test_vertex_uplift_invalid_multiplier_defaults_to_one(): @@ -3695,47 +3585,6 @@ def test_route_image_generation_cost_openai_honors_deployment_input_cost_per_ima assert cost == pytest.approx(0.07) -def test_route_image_generation_cost_gemini_adds_grounding_to_deployment_image_price( - _local_model_cost_map: None, -) -> None: - usage = ImageUsage( - input_tokens=0, - input_tokens_details=ImageUsageInputTokensDetails(image_tokens=0, text_tokens=0), - output_tokens=0, - total_tokens=0, - web_search_requests=3, - ) - - cost = CostCalculatorUtils.route_image_generation_cost_calculator( - model="gemini/gemini-3.1-flash-image-preview", - completion_response=_image_response(usage=usage), - custom_llm_provider="gemini", - call_type="image_generation", - model_info={"output_cost_per_image": 0.1}, - ) - - assert cost == pytest.approx(0.1 + 3 * 0.014) - - -def test_route_image_generation_cost_gemini_bills_tokens_when_no_image_returned( - _local_model_cost_map: None, -) -> None: - usage = ImageUsage( - input_tokens=10, - input_tokens_details=ImageUsageInputTokensDetails(image_tokens=0, text_tokens=10), - output_tokens=1290, - total_tokens=1300, - ) - - cost = CostCalculatorUtils.route_image_generation_cost_calculator( - model="gemini/gemini-3.1-flash-image-preview", - completion_response=ImageResponse(data=[], usage=usage), - custom_llm_provider="gemini", - call_type="image_generation", - model_info={"output_cost_per_image": 0.08}, - ) - - assert cost == pytest.approx(10 * 5e-07 + 1290 * 6e-05) @pytest.mark.parametrize( diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py index 7bae2eaa338..41a2d19b8ab 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py @@ -109,26 +109,6 @@ def test_get_cost_for_built_in_tools_file_search(): assert cost == 0.00 -def test_get_cost_for_anthropic_web_search(): - """ - Test that Anthropic web search cost is tracked when usage.server_tool_use.web_search_requests - is set. Use claude-3-7-sonnet-20250219 (has search_context_cost_per_query) and - custom_llm_provider=anthropic so get_cost_for_anthropic_web_search is invoked. - """ - from litellm.types.utils import ServerToolUse, Usage - - model = "claude-3-7-sonnet-20250219" - usage = Usage(server_tool_use=ServerToolUse(web_search_requests=1)) - cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( - model=model, - usage=usage, - response_object=None, - standard_built_in_tools_params=None, - custom_llm_provider="anthropic", - ) - assert cost > 0.0 - - def test_get_cost_for_anthropic_web_search_with_server_tool_use_dict(): """ Anthropic-compatible passthrough responses can construct Usage from a raw @@ -145,88 +125,6 @@ def test_get_cost_for_anthropic_web_search_with_server_tool_use_dict(): ) -def test_anthropic_web_search_cost_from_raw_response_dict_when_usage_drops_server_tool_use(): - """ - Regression: on the Anthropic /v1/messages sync cost path the response is the raw - Anthropic dict while the reconstructed OpenAI-shape Usage drops server_tool_use. - The web-search fee must still be charged by reading the count off the raw dict, - and the passed-in Usage must not be mutated. - """ - from litellm.types.utils import Usage - - model = "claude-3-7-sonnet-20250219" - web_search_requests = 3 - raw_response = { - "id": "msg_1", - "type": "message", - "role": "assistant", - "model": model, - "content": [{"type": "text", "text": "hi"}], - "stop_reason": "end_turn", - "stop_sequence": None, - "usage": { - "input_tokens": 100, - "output_tokens": 50, - "server_tool_use": {"web_search_requests": web_search_requests}, - }, - } - usage = Usage(prompt_tokens=100, completion_tokens=50, total_tokens=150) - assert getattr(usage, "server_tool_use", None) is None - - cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( - model=model, - usage=usage, - response_object=raw_response, - custom_llm_provider="anthropic", - standard_built_in_tools_params=None, - ) - - per_query_cost = litellm.get_model_info(model)["search_context_cost_per_query"][ - "search_context_size_medium" - ] - assert cost == per_query_cost * web_search_requests - assert cost > 0.0 - assert getattr(usage, "server_tool_use", None) is None - - -def test_anthropic_web_search_cost_from_raw_response_dict_when_usage_is_none(): - """ - Regression: when a caller hands the cost tracker a raw Anthropic dict without a - parallel Usage object, the web-search fee must still be priced per request from - usage.server_tool_use.web_search_requests on the dict instead of falling back to - the flat search_context_size_medium tier. - """ - model = "claude-3-7-sonnet-20250219" - web_search_requests = 4 - raw_response = { - "id": "msg_1", - "type": "message", - "role": "assistant", - "model": model, - "content": [{"type": "text", "text": "hi"}], - "stop_reason": "end_turn", - "stop_sequence": None, - "usage": { - "input_tokens": 100, - "output_tokens": 50, - "server_tool_use": {"web_search_requests": web_search_requests}, - }, - } - - cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( - model=model, - usage=None, - response_object=raw_response, - custom_llm_provider="anthropic", - standard_built_in_tools_params=None, - ) - - per_query_cost = litellm.get_model_info(model)["search_context_cost_per_query"][ - "search_context_size_medium" - ] - assert cost == per_query_cost * web_search_requests - - def test_anthropic_web_search_zero_requests_from_raw_response_charges_zero(): """ Regression: a raw Anthropic dict reporting zero web search requests must price @@ -287,27 +185,6 @@ def test_anthropic_response_usage_block_preserves_server_tool_use(): assert dumped_usage["server_tool_use"] == {"web_search_requests": 2} -@pytest.mark.parametrize( - "model", ["gemini/gemini-2.0-flash-001", "gemini-2.0-flash-001"] -) -def test_get_cost_for_gemini_web_search(model): - """ - Test that the cost for a web search is 0.00 when no response object is provided - """ - from litellm.types.utils import PromptTokensDetailsWrapper, Usage - - usage = Usage( - prompt_tokens_details=PromptTokensDetailsWrapper(web_search_requests=1) - ) - cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( - model=model, - usage=usage, - response_object=None, - standard_built_in_tools_params=None, - ) - assert cost > 0.0 - - def test_completion_cost_includes_web_search_without_standard_built_in_tools_params(): """ Test that completion_cost includes web search cost even when diff --git a/tests/test_litellm/litellm_core_utils/test_fallback_generalizations.py b/tests/test_litellm/litellm_core_utils/test_fallback_generalizations.py index 7928768b3bd..f70b52a7026 100644 --- a/tests/test_litellm/litellm_core_utils/test_fallback_generalizations.py +++ b/tests/test_litellm/litellm_core_utils/test_fallback_generalizations.py @@ -979,10 +979,6 @@ def test_shipped_tool_search_rule_fills_mapped_claude_entries_without_flag(shipp assert "supports_tool_search" not in litellm.model_cost[key] assert litellm.get_model_info(model, custom_llm_provider=provider)["supports_tool_search"] is True - assert "supports_tool_search" not in litellm.model_cost["claude-opus-4-1"] - opus_4_1_info = litellm.get_model_info("claude-opus-4-1", custom_llm_provider="anthropic") - assert opus_4_1_info.get("supports_tool_search") is None - assert "supports_tool_search" not in litellm.model_cost["azure_ai/claude-opus-5"] azure_opus_5_info = litellm.get_model_info("claude-opus-5", custom_llm_provider="azure_ai") assert azure_opus_5_info.get("supports_tool_search") is None diff --git a/tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py b/tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py index 262dabb7c1b..00977d9c3ee 100644 --- a/tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py +++ b/tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py @@ -218,7 +218,6 @@ def test_shipped_backup_marks_claude_4_6_plus_adaptive_not_4_0(): assert backup[adaptive]["supports_adaptive_thinking"] is True, adaptive for non_adaptive in [ - "claude-opus-4-20250514", "us.anthropic.claude-opus-4-20250514-v1:0", "claude-opus-4-5", ]: diff --git a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py index 4541250e896..5bdc0e9f8b8 100644 --- a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py +++ b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py @@ -8389,21 +8389,6 @@ def test_get_assembled_streaming_response_bills_a_provider_reported_usage_cost() assert logging_obj._response_cost_calculator(result=assembled) == 0.0042 -def test_get_assembled_streaming_response_without_usage_cost_leaves_pricing_to_the_price_map(): - logging_obj = _responses_stream_logging_obj() - now = datetime.datetime.now() - - assembled = logging_obj._get_assembled_streaming_response( - result=_completed_responses_event(ResponseAPIUsage(input_tokens=12, output_tokens=2, total_tokens=14)), - start_time=now, - end_time=now, - is_async=True, - streaming_chunks=[], - ) - - assert "additional_headers" not in assembled._hidden_params - price_map_cost = logging_obj._response_cost_calculator(result=assembled) - assert price_map_cost is not None and 0 < price_map_cost != 0.0042 def test_response_cost_calculator_prices_terminal_responses_event_from_its_response(): diff --git a/tests/test_litellm/litellm_core_utils/test_streaming_chunk_builder_server_tool_use.py b/tests/test_litellm/litellm_core_utils/test_streaming_chunk_builder_server_tool_use.py index 75508917a1e..e8a7ef74bfa 100644 --- a/tests/test_litellm/litellm_core_utils/test_streaming_chunk_builder_server_tool_use.py +++ b/tests/test_litellm/litellm_core_utils/test_streaming_chunk_builder_server_tool_use.py @@ -99,29 +99,3 @@ def test_stream_chunk_builder_coerces_server_tool_use_to_pydantic(): assert server_tool_use.web_search_requests == 3 -def test_completion_cost_does_not_raise_on_streaming_web_search_response(): - """ - Regression: completion_cost(...) must not raise AttributeError when the - response was reconstructed by stream_chunk_builder from a streaming - Anthropic web_search call. - """ - chunks = [ - _make_text_chunk("hello"), - _make_finish_chunk_with_usage_dict_server_tool_use(), - ] - - rebuilt = stream_chunk_builder(chunks) - assert rebuilt is not None - - # The exact dollar amount depends on the model-pricing table; what matters - # for this regression is that it does NOT raise AttributeError on - # `dict has no attribute 'web_search_requests'`. - try: - cost = completion_cost(completion_response=rebuilt) - except AttributeError as e: # pragma: no cover - regression guard - pytest.fail( - "completion_cost raised AttributeError after stream_chunk_builder " - f"(issue #26153 regression): {e}" - ) - - assert isinstance(cost, (int, float)) diff --git a/tests/test_litellm/litellm_core_utils/test_token_counter.py b/tests/test_litellm/litellm_core_utils/test_token_counter.py index 5ce6a4b1ce9..eccf44a1bda 100644 --- a/tests/test_litellm/litellm_core_utils/test_token_counter.py +++ b/tests/test_litellm/litellm_core_utils/test_token_counter.py @@ -633,9 +633,6 @@ def test_openai_token_with_image_and_text(): "model, base_model, input_tokens, user_max_tokens, expected_value", [ ("random-model", "random-model", 1024, 1024, 1024), - ("command", "command", 1000000, None, None), # model max = 4096 - ("command", "command", 4000, 256, 96), # model max = 4096 - ("command", "command", 4000, 10, 10), # model max = 4096 ("gpt-3.5-turbo", "gpt-3.5-turbo", 4000, 5000, 4096), # model max output = 4096 ], ) diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py index db5da28c024..f92c610df24 100644 --- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py @@ -5580,43 +5580,6 @@ def test_tool_config_cachepoint_not_placed_or_credited_for_model_without_prompt_ assert "litellm_gateway_injected_cache" not in bucket -def test_translate_response_format_json_schema_still_injects_tool(): - """ - response_format with an explicit json_schema should still use the - synthetic tool call approach (for models that don't support native - structured outputs). - """ - config = AmazonConverseConfig() - - response_format = { - "type": "json_schema", - "json_schema": { - "name": "FactResult", - "schema": { - "type": "object", - "properties": { - "facts": { - "type": "array", - "items": {"type": "string"}, - }, - }, - "required": ["facts"], - }, - }, - } - - optional_params: dict = {} - result = config._translate_response_format_param( - value=response_format, - model="anthropic.claude-3-haiku-20240307-v1:0", - optional_params=optional_params, - non_default_params={"response_format": response_format}, - is_thinking_enabled=False, - ) - - assert result["json_mode"] is True - assert "tools" in result - assert "tool_choice" in result def test_transform_response_finish_reason_stop_when_json_mode_filters_all_tools(): diff --git a/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py b/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py index afac7b0bc1a..de0e547c0cd 100644 --- a/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py +++ b/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py @@ -153,14 +153,6 @@ def test_uncached_request_bills_every_prompt_token_at_the_input_rate(local_model assert completion_cost == pytest.approx(200 * info["output_cost_per_token"]) -def test_legacy_endpoint_names_still_resolve(local_model_cost_map: None) -> None: - info: Final = _model_info("databricks/databricks-mixtral-8x7b-instruct") - usage: Final = Usage(prompt_tokens=100, completion_tokens=100, total_tokens=200) - - prompt_cost, completion_cost = cost_per_token(model="databricks/mixtral-8x7b-instruct-v0.1", usage=usage) - - assert prompt_cost == pytest.approx(100 * info["input_cost_per_token"]) - assert completion_cost == pytest.approx(100 * info["output_cost_per_token"]) @pytest.mark.parametrize("model", NEW_MODELS) diff --git a/tests/test_litellm/llms/gemini/test_cost_calculator.py b/tests/test_litellm/llms/gemini/test_cost_calculator.py index 5eed11dff03..b2633c6091b 100644 --- a/tests/test_litellm/llms/gemini/test_cost_calculator.py +++ b/tests/test_litellm/llms/gemini/test_cost_calculator.py @@ -200,172 +200,12 @@ def test_maps_no_usage_details(): assert cost_per_google_maps_grounding_request(usage=usage, model_info=model_info) == 0.0 -def test_gemini_image_edit_cost_prefers_token_usage_metadata(monkeypatch): - monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") - litellm.model_cost = litellm.get_model_cost_map(url="") - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - - input_text_tokens = 20 - input_image_tokens = 1120 - output_image_tokens = 1120 - prompt_tokens = input_text_tokens + input_image_tokens - image_response = ImageResponse( - data=[ImageObject(b64_json="img1"), ImageObject(b64_json="img2")], - usage=ImageUsage( - input_tokens=prompt_tokens, - input_tokens_details=ImageUsageInputTokensDetails( - text_tokens=input_text_tokens, - image_tokens=input_image_tokens, - ), - output_tokens=output_image_tokens, - total_tokens=prompt_tokens + output_image_tokens, - ), - ) - - cost = gemini_image_edit_cost_calculator( - model=model, - image_response=image_response, - ) - - expected_cost = ( - prompt_tokens * model_info["input_cost_per_token"] - + output_image_tokens * model_info["output_cost_per_image_token"] - ) - flat_image_cost = ( - len(image_response.data or []) * model_info["output_cost_per_image"] - ) - assert round(cost, 10) == round(expected_cost, 10) - assert cost != flat_image_cost -def test_gemini_image_edit_cost_uses_output_token_details(monkeypatch): - monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") - litellm.model_cost = litellm.get_model_cost_map(url="") - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - - input_text_tokens = 20 - output_text_tokens = 213 - output_image_tokens = 1120 - output_tokens = output_text_tokens + output_image_tokens - image_response = ImageResponse( - data=[ImageObject(b64_json="img1")], - usage=ImageUsage( - input_tokens=input_text_tokens, - input_tokens_details=ImageUsageInputTokensDetails( - text_tokens=input_text_tokens, - image_tokens=0, - ), - output_tokens=output_tokens, - total_tokens=input_text_tokens + output_tokens, - prompt_tokens=input_text_tokens, - completion_tokens=output_tokens, - prompt_tokens_details={ - "text_tokens": input_text_tokens, - "image_tokens": 0, - }, - completion_tokens_details={ - "text_tokens": output_text_tokens, - "image_tokens": output_image_tokens, - }, - output_tokens_details={ - "text_tokens": output_text_tokens, - "image_tokens": output_image_tokens, - }, - ), - ) - - cost = gemini_image_edit_cost_calculator( - model=model, - image_response=image_response, - ) - - expected_cost = ( - input_text_tokens * model_info["input_cost_per_token"] - + output_text_tokens * model_info["output_cost_per_token"] - + output_image_tokens * model_info["output_cost_per_image_token"] - ) - all_output_as_image_cost = ( - input_text_tokens * model_info["input_cost_per_token"] - + (output_text_tokens + output_image_tokens) - * model_info["output_cost_per_image_token"] - ) - assert round(cost, 10) == round(expected_cost, 10) - assert cost != all_output_as_image_cost -def test_gemini_image_generation_cost_uses_output_token_details(monkeypatch): - monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") - litellm.model_cost = litellm.get_model_cost_map(url="") - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - - input_text_tokens = 20 - output_text_tokens = 213 - output_image_tokens = 1120 - output_tokens = output_text_tokens + output_image_tokens - image_response = ImageResponse( - data=[ImageObject(b64_json="img1")], - usage=ImageUsage( - input_tokens=input_text_tokens, - input_tokens_details=ImageUsageInputTokensDetails( - text_tokens=input_text_tokens, - image_tokens=0, - ), - output_tokens=output_tokens, - total_tokens=input_text_tokens + output_tokens, - prompt_tokens=input_text_tokens, - completion_tokens=output_tokens, - prompt_tokens_details={ - "text_tokens": input_text_tokens, - "image_tokens": 0, - }, - completion_tokens_details={ - "text_tokens": output_text_tokens, - "image_tokens": output_image_tokens, - }, - output_tokens_details={ - "text_tokens": output_text_tokens, - "image_tokens": output_image_tokens, - }, - ), - ) - - cost = gemini_image_generation_cost_calculator( - model=model, - image_response=image_response, - ) - - expected_cost = ( - input_text_tokens * model_info["input_cost_per_token"] - + output_text_tokens * model_info["output_cost_per_token"] - + output_image_tokens * model_info["output_cost_per_image_token"] - ) - all_output_as_image_cost = ( - input_text_tokens * model_info["input_cost_per_token"] - + (output_text_tokens + output_image_tokens) - * model_info["output_cost_per_image_token"] - ) - assert round(cost, 10) == round(expected_cost, 10) - assert cost != all_output_as_image_cost -def test_gemini_image_edit_cost_falls_back_to_flat_image_pricing(monkeypatch): - monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") - litellm.model_cost = litellm.get_model_cost_map(url="") - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - image_response = ImageResponse( - data=[ImageObject(b64_json="img1"), ImageObject(b64_json="img2")] - ) - - cost = gemini_image_edit_cost_calculator( - model=model, - image_response=image_response, - ) - - assert cost == len(image_response.data or []) * model_info["output_cost_per_image"] def _image_response_with_web_search(web_search_requests): @@ -383,43 +223,8 @@ def _image_response_with_web_search(web_search_requests): return ImageResponse(data=[ImageObject(b64_json="img1")], usage=usage) -def test_gemini_image_generation_cost_adds_web_search_grounding(monkeypatch): - monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") - litellm.model_cost = litellm.get_model_cost_map(url="") - model = "gemini/gemini-3-pro-image-preview" - model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini") - - grounded = gemini_image_generation_cost_calculator( - model=model, - image_response=_image_response_with_web_search(2), - ) - ungrounded = gemini_image_generation_cost_calculator( - model=model, - image_response=_image_response_with_web_search(None), - ) - - expected_web_search_cost = cost_per_web_search_request( - usage=_make_usage(2), model_info=model_info - ) - assert expected_web_search_cost > 0 - assert round(grounded - ungrounded, 10) == round(expected_web_search_cost, 10) -def test_gemini_image_generation_cost_no_web_search_when_absent(monkeypatch): - monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") - litellm.model_cost = litellm.get_model_cost_map(url="") - model = "gemini/gemini-3-pro-image-preview" - - cost_zero = gemini_image_generation_cost_calculator( - model=model, - image_response=_image_response_with_web_search(0), - ) - cost_none = gemini_image_generation_cost_calculator( - model=model, - image_response=_image_response_with_web_search(None), - ) - - assert cost_zero == cost_none @pytest.mark.parametrize( diff --git a/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py b/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py index f1f1978b06f..b1d7e49fbac 100644 --- a/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py +++ b/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py @@ -371,62 +371,8 @@ def test_x_initiator_header_system_only_messages(): assert headers["X-Initiator"] == "user" -def test_get_supported_openai_params_claude_model(): - """Test that Claude models with extended thinking support have thinking and reasoning parameters.""" - config = GithubCopilotConfig() - - # Test Claude 4 model supports thinking and reasoning_effort parameters - supported_params = config.get_supported_openai_params("claude-sonnet-4-20250514") - assert "thinking" in supported_params - assert "reasoning_effort" in supported_params - - # Test Claude 3-7 model supports thinking and reasoning_effort parameters - supported_params_claude37 = config.get_supported_openai_params( - "claude-3-7-sonnet-20250219" - ) - assert "thinking" in supported_params_claude37 - assert "reasoning_effort" in supported_params_claude37 - - # Test Claude 3.5 model does NOT support thinking parameters (no extended thinking) - supported_params_claude35 = config.get_supported_openai_params("claude-3.5-sonnet") - assert "thinking" not in supported_params_claude35 - assert "reasoning_effort" not in supported_params_claude35 - - # Test non-Claude model doesn't include thinking parameters but may include reasoning_effort - supported_params_gpt = config.get_supported_openai_params("gpt-4o") - assert "thinking" not in supported_params_gpt - # gpt-4o should NOT have reasoning_effort (not a reasoning model) - assert "reasoning_effort" not in supported_params_gpt - - # Test O-series reasoning models include reasoning_effort but not thinking - supported_params_o3 = config.get_supported_openai_params("o3-mini") - assert "thinking" not in supported_params_o3 - # o3-mini should have reasoning_effort (it's an O-series reasoning model) - assert "reasoning_effort" in supported_params_o3 -def test_get_supported_openai_params_case_insensitive(): - """Test that Claude model detection is case-insensitive for models with extended thinking.""" - config = GithubCopilotConfig() - - # Test uppercase Claude 4 model with full model name - supported_params_upper = config.get_supported_openai_params( - "CLAUDE-SONNET-4-20250514" - ) - assert "thinking" in supported_params_upper - assert "reasoning_effort" in supported_params_upper - - # Test mixed case Claude 3-7 model (has extended thinking) with full model name - supported_params_mixed = config.get_supported_openai_params( - "Claude-3-7-Sonnet-20250219" - ) - assert "thinking" in supported_params_mixed - assert "reasoning_effort" in supported_params_mixed - - # Test that Claude 3.5 models don't have thinking support (case insensitive) - supported_params_35 = config.get_supported_openai_params("CLAUDE-3.5-SONNET") - assert "thinking" not in supported_params_35 - assert "reasoning_effort" not in supported_params_35 def test_copilot_vision_request_header_with_image(): diff --git a/tests/test_litellm/llms/openai/test_gpt5_transformation.py b/tests/test_litellm/llms/openai/test_gpt5_transformation.py index 0adc7fa8d5f..41f5816600f 100644 --- a/tests/test_litellm/llms/openai/test_gpt5_transformation.py +++ b/tests/test_litellm/llms/openai/test_gpt5_transformation.py @@ -38,10 +38,6 @@ def test_gpt5_supports_reasoning_effort(config: OpenAIConfig): assert "reasoning_effort" in config.get_supported_openai_params(model="gpt-5-mini") -def test_gpt5_chat_does_not_support_reasoning_effort(config: OpenAIConfig): - assert "reasoning_effort" not in config.get_supported_openai_params( - model="gpt-5-chat-latest" - ) def test_gpt5_chat_supports_temperature(config: OpenAIConfig): @@ -174,10 +170,6 @@ def test_gpt5_codex_unsupported_params_drop(config: OpenAIConfig): assert param not in config.get_supported_openai_params(model="gpt-5-codex") -def test_gpt5_codex_supports_tool_choice(gpt5_config: OpenAIGPT5Config): - """Test that GPT-5-Codex supports tool_choice parameter.""" - supported_params = gpt5_config.get_supported_openai_params(model="gpt-5-codex") - assert "tool_choice" in supported_params def test_gpt5_codex_supports_function_calling(config: OpenAIConfig): @@ -246,14 +238,6 @@ def test_gpt5_1_reasoning_effort_none(config: OpenAIConfig): assert params["reasoning_effort"] == effort -def test_gpt5_1_codex_max_allows_reasoning_effort_xhigh(config: OpenAIConfig): - params = config.map_openai_params( - non_default_params={"reasoning_effort": "xhigh"}, - optional_params={}, - model="gpt-5.1-codex-max", - drop_params=False, - ) - assert params["reasoning_effort"] == "xhigh" def test_gpt5_rejects_reasoning_effort_xhigh_for_other_models(config: OpenAIConfig): diff --git a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py index a796e2ac607..8b0662de3f9 100644 --- a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py +++ b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py @@ -5948,8 +5948,8 @@ def test_calculate_web_search_requests_counts_unique_queries(): @pytest.mark.parametrize("custom_llm_provider", ["gemini", "vertex_ai"]) @pytest.mark.parametrize( "model", - ["gemini-2.5-flash", "gemini-3-pro-preview"], - ids=["thinking_budget_mapper", "thinking_level_mapper"], + ["gemini-2.5-flash"], + ids=["thinking_budget_mapper"], ) @pytest.mark.parametrize("reasoning_effort", ["banana", "xhigh"]) def test_invalid_reasoning_effort_is_a_400_not_a_500(custom_llm_provider, model, reasoning_effort): diff --git a/tests/test_litellm/llms/vertex_ai/test_vertex_passthrough_logging_handler.py b/tests/test_litellm/llms/vertex_ai/test_vertex_passthrough_logging_handler.py index 58e7529309a..4199e57d2f9 100644 --- a/tests/test_litellm/llms/vertex_ai/test_vertex_passthrough_logging_handler.py +++ b/tests/test_litellm/llms/vertex_ai/test_vertex_passthrough_logging_handler.py @@ -238,31 +238,3 @@ def test_audio_predict_response_supports_bytes_base64_encoded( assert logging_obj.model_call_details["response_cost"] == pytest.approx(0.06) -def test_image_predict_response_is_not_billed_as_audio( - local_model_cost_map: None, -) -> None: - logging_obj = MagicMock() - logging_obj.model_call_details = {} - response = httpx.Response( - status_code=200, - json={"predictions": [{"bytesBase64Encoded": "frame", "mimeType": "image/png"}]}, - ) - - result = VertexPassthroughLoggingHandler.vertex_passthrough_handler( - httpx_response=response, - logging_obj=logging_obj, - url_route=( - "/v1/projects/test/locations/us-central1/publishers/google/models/imagen-4.0-generate-001:predict" - ), - result=response.text, - start_time=datetime.now(), - end_time=datetime.now(), - cache_hit=False, - request_body={"instances": [{"prompt": "a red cube"}]}, - ) - - assert isinstance(result["result"], litellm.ImageResponse) - assert logging_obj.call_type == PassthroughCallTypes.passthrough_image_generation.value - assert result["kwargs"]["response_cost"] == pytest.approx( - litellm.model_cost["vertex_ai/imagen-4.0-generate-001"]["output_cost_per_image"] - ) diff --git a/tests/test_litellm/llms/wandb/test_wandb_chat_transformation.py b/tests/test_litellm/llms/wandb/test_wandb_chat_transformation.py index a25ed585ecc..5c168d84766 100644 --- a/tests/test_litellm/llms/wandb/test_wandb_chat_transformation.py +++ b/tests/test_litellm/llms/wandb/test_wandb_chat_transformation.py @@ -37,10 +37,6 @@ WANDB_REASONING_MODELS: Final = ( "Qwen/Qwen3.5-35B-A3B", "zai-org/GLM-5.2", "moonshotai/Kimi-K2.5", - "MiniMaxAI/MiniMax-M2.5", - "zai-org/GLM-4.5", - "Qwen/Qwen3-235B-A22B-Thinking-2507", - "deepseek-ai/DeepSeek-R1-0528", ) diff --git a/tests/test_litellm/llms/xai/test_xai_cost_calculator.py b/tests/test_litellm/llms/xai/test_xai_cost_calculator.py index cf3bc73a225..6065f1053e7 100644 --- a/tests/test_litellm/llms/xai/test_xai_cost_calculator.py +++ b/tests/test_litellm/llms/xai/test_xai_cost_calculator.py @@ -152,83 +152,10 @@ class TestXAICostCalculator: setattr(reported, "server_side_tool_usage_details", {"web_search_calls": 3}) assert get_cost_for_web_search_request("xai", reported, {}) == 0.0 - def test_no_reported_cost_falls_back_to_token_math(self): - """Absent the provider figure, nothing changes for existing callers.""" - usage = Usage(prompt_tokens=100, completion_tokens=200, total_tokens=300) - prompt_cost, completion_cost = cost_per_token(model="grok-4-latest", usage=usage) - assert prompt_cost > 0.0 - assert completion_cost > 0.0 - def test_malformed_reported_cost_falls_back_to_token_math(self): - """A junk value must not fail the request, fall back to calculating.""" - usage = Usage(prompt_tokens=100, completion_tokens=200, total_tokens=300) - setattr(usage, "cost", "not-a-number") - prompt_cost, completion_cost = cost_per_token(model="grok-4-latest", usage=usage) - - assert prompt_cost > 0.0 - assert completion_cost > 0.0 - - def test_boolean_reported_cost_falls_back_to_token_math(self): - """True is an int in python and would otherwise be billed as $1.""" - usage = Usage(prompt_tokens=100, completion_tokens=200, total_tokens=300) - setattr(usage, "cost", True) - - prompt_cost, completion_cost = cost_per_token(model="grok-4-latest", usage=usage) - - assert prompt_cost > 0.0 - assert completion_cost > 0.0 - assert completion_cost != 1.0 - - def test_negative_reported_cost_is_rejected(self): - """A negative amount must never reach spend tracking. - - A caller who can set api_base controls the response body, so trusting a - negative figure would let them subtract from their own recorded spend and - slip past a budget. Fall back to token pricing instead, and keep charging - the web search surcharge, since no trustworthy total was reported. - """ - usage = Usage( - prompt_tokens=100, - completion_tokens=200, - total_tokens=300, - cost=-0.0037756, - ) - setattr(usage, "server_side_tool_usage_details", {"web_search_calls": 3}) - - prompt_cost, completion_cost = cost_per_token(model="grok-4-latest", usage=usage) - - assert prompt_cost > 0.0 - assert completion_cost > 0.0 - assert cost_per_web_search_request(usage=usage, model_info={}) > 0.0 - - def test_non_finite_reported_cost_is_rejected(self): - """NaN compares false against every budget threshold. - - Usage stores a provider supplied cost without validating it, so a caller who - controls the response body could report NaN and leave spend >= max_budget - false for the life of the key rather than mispricing one request. The - infinities are refused alongside it. Fall back to token pricing and keep - charging the web search surcharge, since no trustworthy total was reported. - """ - for reported_cost in (float("nan"), float("inf"), float("-inf")): - usage = Usage( - prompt_tokens=100, - completion_tokens=200, - total_tokens=300, - cost=reported_cost, - ) - setattr(usage, "server_side_tool_usage_details", {"web_search_calls": 3}) - - prompt_cost, completion_cost = cost_per_token(model="grok-4-latest", usage=usage) - - assert math.isfinite(prompt_cost), reported_cost - assert math.isfinite(completion_cost), reported_cost - assert prompt_cost > 0.0, reported_cost - assert completion_cost > 0.0, reported_cost - assert cost_per_web_search_request(usage=usage, model_info={}) > 0.0, reported_cost def test_zero_reported_cost_is_honoured(self): """A reported zero is a real answer, not a missing value.""" diff --git a/tests/test_litellm/llms/xai/test_xai_redirected_slug_pricing.py b/tests/test_litellm/llms/xai/test_xai_redirected_slug_pricing.py deleted file mode 100644 index 83e8925f70b..00000000000 --- a/tests/test_litellm/llms/xai/test_xai_redirected_slug_pricing.py +++ /dev/null @@ -1,102 +0,0 @@ -""" -xAI retired eight slugs on 2026-05-15 but kept them resolvable: chat slugs redirect to -grok-4.3 and bill at grok-4.3's rates, while the grok-code-fast slugs are aliases of -grok-build-0.1 and bill at its rates, so the registry must price them that way or spend -tracking is wrong. The grok-3-beta, grok-3-fast, grok-3-mini, and grok-4-1-fast slugs -are absent from /v1/language-models and resolve to grok-4.3 the same way (the chat -response names grok-4.3 as the served model), so they carry grok-4.3's rates too. -https://docs.x.ai/developers/migration/may-15-retirement -https://docs.x.ai/developers/models/grok-build-0.1 -""" - -from __future__ import annotations - -import json -from pathlib import Path - -import pytest - -REPO_ROOT = Path(__file__).parents[4] -PRICES_PATH = REPO_ROOT / "model_prices_and_context_window.json" -BACKUP_PRICES_PATH = REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json" -MAP_PATHS = (PRICES_PATH, BACKUP_PRICES_PATH) - -REDIRECT_TARGET = "xai/grok-4.3" -GROK_3_MINI_SLUGS = ( - "xai/grok-3-mini", - "xai/grok-3-mini-beta", - "xai/grok-3-mini-fast", - "xai/grok-3-mini-fast-beta", - "xai/grok-3-mini-fast-latest", - "xai/grok-3-mini-latest", -) -REDIRECTED_SLUGS = ( - "xai/grok-3", - "xai/grok-3-beta", - "xai/grok-3-fast-beta", - "xai/grok-3-fast-latest", - "xai/grok-3-latest", - *GROK_3_MINI_SLUGS, - "xai/grok-4", - "xai/grok-4-0709", - "xai/grok-4-1-fast", - "xai/grok-4-1-fast-non-reasoning", - "xai/grok-4-1-fast-non-reasoning-latest", - "xai/grok-4-1-fast-reasoning", - "xai/grok-4-1-fast-reasoning-latest", - "xai/grok-4-fast-non-reasoning", - "xai/grok-4-fast-reasoning", - "xai/grok-4-latest", -) -CODE_REDIRECT_TARGET = "xai/grok-build-0.1" -CODE_SLUGS = ( - "xai/grok-code-fast", - "xai/grok-code-fast-1", - "xai/grok-code-fast-1-0825", -) -BASE_COST_FIELDS = ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost") -TIER_COST_FIELDS = ( - "input_cost_per_token_above_200k_tokens", - "output_cost_per_token_above_200k_tokens", - "cache_read_input_token_cost_above_200k_tokens", -) - - -@pytest.fixture(scope="module", params=[p.name for p in MAP_PATHS]) -def cost_map(request: pytest.FixtureRequest) -> dict: - path = next(p for p in MAP_PATHS if p.name == request.param) - return json.loads(path.read_text(encoding="utf-8")) - - -@pytest.mark.parametrize("slug", REDIRECTED_SLUGS) -def test_redirected_slug_bills_at_the_target_rate(cost_map: dict, slug: str): - target = cost_map[REDIRECT_TARGET] - entry = cost_map[slug] - for field in BASE_COST_FIELDS: - assert entry[field] == target[field], field - - -@pytest.mark.parametrize("slug", CODE_SLUGS) -def test_code_slug_bills_at_grok_build_rate(cost_map: dict, slug: str): - """grok-code-fast* are aliases of grok-build-0.1, not grok-4.3 redirects.""" - target = cost_map[CODE_REDIRECT_TARGET] - entry = cost_map[slug] - for field in (*BASE_COST_FIELDS, *TIER_COST_FIELDS): - assert entry[field] == target[field], field - - -@pytest.mark.parametrize("slug", REDIRECTED_SLUGS) -def test_redirected_slug_carries_the_target_tier_rates(cost_map: dict, slug: str): - """The request executes as grok-4.3, so it is tiered at grok-4.3's 200k boundary.""" - target = cost_map[REDIRECT_TARGET] - entry = cost_map[slug] - for field in TIER_COST_FIELDS: - assert entry[field] == target[field], field - assert {k for k in entry if "_above_" in k} == {k for k in target if "_above_" in k} - - -def test_both_cost_maps_agree_on_the_redirected_slugs(): - prices = json.loads(PRICES_PATH.read_text(encoding="utf-8")) - backup = json.loads(BACKUP_PRICES_PATH.read_text(encoding="utf-8")) - for slug in (*REDIRECTED_SLUGS, *CODE_SLUGS, REDIRECT_TARGET, CODE_REDIRECT_TARGET): - assert prices[slug] == backup[slug], slug diff --git a/tests/test_litellm/proxy/auth/test_auth_checks.py b/tests/test_litellm/proxy/auth/test_auth_checks.py index 14b739e60ba..ffba53a5b7a 100644 --- a/tests/test_litellm/proxy/auth/test_auth_checks.py +++ b/tests/test_litellm/proxy/auth/test_auth_checks.py @@ -8057,7 +8057,6 @@ def test_model_has_no_cost_mapping_no_model_or_router_is_false(): [ "azure/speech/azure-tts", "mistral/mistral-ocr-latest", - "vertex_ai/imagen-3.0-generate-001", "dashscope/qwen-flash", ], ) diff --git a/tests/test_litellm/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py b/tests/test_litellm/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py index ba8b5fa3ac4..094320225cd 100644 --- a/tests/test_litellm/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py +++ b/tests/test_litellm/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py @@ -588,43 +588,6 @@ class TestAzureAnthropicCostCalculation: == "claude-3-5-haiku-20241022" ) - def test_passthrough_logging_sets_response_cost_with_server_tool_use_dict(self): - from litellm.types.utils import Choices, Message, ModelResponse - - logging_obj = self._create_mock_logging_obj(model="claude-3-7-sonnet-20250219") - logging_obj.get_router_model_id.return_value = None - logging_obj.litellm_params = {} - - response = ModelResponse( - id="test-id", - choices=[ - Choices( - finish_reason="stop", - index=0, - message=Message(content="test", role="assistant"), - ) - ], - created=1234567890, - model="claude-3-7-sonnet-20250219", - usage={ - "prompt_tokens": 10, - "completion_tokens": 5, - "total_tokens": 15, - "server_tool_use": {"web_search_requests": 1}, - }, - ) - - kwargs = AnthropicPassthroughLoggingHandler._create_anthropic_response_logging_payload( - litellm_model_response=response, - model="claude-3-7-sonnet-20250219", - kwargs={}, - start_time=datetime.now(), - end_time=datetime.now(), - logging_obj=logging_obj, - ) - - assert "response_cost" in kwargs - assert kwargs["response_cost"] > 0 class TestAnthropicBatchPassthroughCostTracking: @@ -2355,42 +2318,6 @@ class TestAnthropicResponseCostRecordedOnModelCallDetails: model_call_details["response_cost"], not from kwargs, so the streaming payload builder must record it there or streaming pass-through logs $0.""" - def test_create_payload_records_response_cost_on_model_call_details(self): - from litellm.types.utils import Choices, Message, ModelResponse - - logging_obj = MagicMock() - logging_obj.model_call_details = {} - logging_obj.get_router_model_id.return_value = None - logging_obj.litellm_params = {} - logging_obj.litellm_call_id = "test-call-id" - - response = ModelResponse( - id="test-id", - choices=[ - Choices( - finish_reason="stop", - index=0, - message=Message(content="hello", role="assistant"), - ) - ], - created=1234567890, - model="claude-3-7-sonnet-20250219", - usage={"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}, - ) - - kwargs = AnthropicPassthroughLoggingHandler._create_anthropic_response_logging_payload( - litellm_model_response=response, - model="claude-3-7-sonnet-20250219", - kwargs={}, - start_time=datetime.now(), - end_time=datetime.now(), - logging_obj=logging_obj, - ) - - assert ( - logging_obj.model_call_details["response_cost"] == kwargs["response_cost"] - ) - assert logging_obj.model_call_details["response_cost"] > 0 class TestAnthropicPassthroughFastMode: diff --git a/tests/test_litellm/proxy/pass_through_endpoints/test_vertex_ai_batch_passthrough.py b/tests/test_litellm/proxy/pass_through_endpoints/test_vertex_ai_batch_passthrough.py index 1d2d7d4d5c3..46f024366ec 100644 --- a/tests/test_litellm/proxy/pass_through_endpoints/test_vertex_ai_batch_passthrough.py +++ b/tests/test_litellm/proxy/pass_through_endpoints/test_vertex_ai_batch_passthrough.py @@ -462,30 +462,6 @@ class TestVertexAIBatchPassthroughHandler: assert mock_store.call_args[1]["unified_object_id"] assert mock_store.call_args[1]["is_batch_create"] is expected - def test_batch_cost_calculation_integration(self): - """Single Vertex AI response → non-zero cost with correct token counts.""" - from litellm.batches.batch_utils import calculate_vertex_ai_batch_cost_and_usage - - vertex_ai_batch_responses = [ - { - "response": { - "usageMetadata": { - "promptTokenCount": 10, - "candidatesTokenCount": 5, - "totalTokenCount": 15, - } - } - } - ] - - result = calculate_vertex_ai_batch_cost_and_usage( - vertex_ai_batch_responses, model_name="gemini-2.0-flash-001" - ) - - assert result.usage.total_tokens == 15 - assert result.usage.prompt_tokens == 10 - assert result.usage.completion_tokens == 5 - assert result.cost > 0, "batch_cost_calculator should return a non-zero cost" def test_batch_response_transformation(self): """Test transformation of Vertex AI batch responses to OpenAI format""" @@ -639,76 +615,7 @@ class TestVertexAIBatchCostCalculation: batch_cost_calculator — no VertexGeminiConfig transformation involved. """ - def test_should_aggregate_cost_and_usage_across_responses(self): - """Two successful responses → costs and token counts are summed.""" - from litellm.batches.batch_utils import calculate_vertex_ai_batch_cost_and_usage - responses = [ - { - "response": { - "usageMetadata": { - "promptTokenCount": 10, - "candidatesTokenCount": 5, - "totalTokenCount": 15, - } - } - }, - { - "response": { - "usageMetadata": { - "promptTokenCount": 8, - "candidatesTokenCount": 3, - "totalTokenCount": 11, - } - } - }, - ] - - result = calculate_vertex_ai_batch_cost_and_usage( - responses, model_name="gemini-2.0-flash-001" - ) - - assert result.usage.prompt_tokens == 18 - assert result.usage.completion_tokens == 8 - assert result.usage.total_tokens == 26 - assert result.cost > 0, "batch_cost_calculator should return a non-zero cost" - - def test_should_skip_responses_with_null_response_body(self): - """Failed lines (response: None) are skipped without error.""" - from litellm.batches.batch_utils import calculate_vertex_ai_batch_cost_and_usage - - responses = [ - { - "response": { - "usageMetadata": { - "promptTokenCount": 10, - "candidatesTokenCount": 5, - "totalTokenCount": 15, - } - } - }, - {"status": "JOB_STATE_FAILED", "response": None}, - { - "response": { - "usageMetadata": { - "promptTokenCount": 8, - "candidatesTokenCount": 3, - "totalTokenCount": 11, - } - } - }, - ] - - result = calculate_vertex_ai_batch_cost_and_usage( - responses, model_name="gemini-2.0-flash-001" - ) - - assert result.usage.prompt_tokens == 18 - assert result.usage.completion_tokens == 8 - assert result.usage.total_tokens == 26 - assert result.cost > 0 - assert result.successful_requests == 2 - assert result.failed_requests == 1 def test_should_return_zeros_for_empty_response_list(self): """Empty input → zero cost and zero usage.""" @@ -739,143 +646,4 @@ class TestVertexAIBatchCostCalculation: assert result.usage.completion_tokens == 0 assert result.usage.total_tokens == 0 - @pytest.mark.asyncio - async def test_openai_shaped_output_records_nonzero_cost_and_usage(self): - """ - Regression test for the bug where Vertex batch cost/usage was always 0. - After PR #25627 (transform_file_content_response), the GCS predictions.jsonl - is rewritten into OpenAI batch shape before the cost-tracking path sees it. - With disable_vertex_batch_output_transformation=False (default), the cost - dispatch must fall through to the generic aggregation path rather than - calling calculate_vertex_ai_batch_cost_and_usage (which only reads raw - usageMetadata fields). - """ - import litellm - from litellm.batches.batch_utils import calculate_batch_cost_and_usage - - openai_shaped_responses = [ - { - "id": "batch_req_abc123", - "custom_id": "request-1", - "response": { - "status_code": 200, - "request_id": "chatcmpl-xyz", - "body": { - "id": "chatcmpl-xyz", - "object": "chat.completion", - "model": "gemini-2.0-flash-001", - "choices": [ - { - "index": 0, - "message": {"role": "assistant", "content": "Hello!"}, - "finish_reason": "stop", - } - ], - "usage": { - "prompt_tokens": 10, - "completion_tokens": 5, - "total_tokens": 15, - }, - }, - }, - "error": None, - }, - { - "id": "batch_req_def456", - "custom_id": "request-2", - "response": { - "status_code": 200, - "request_id": "chatcmpl-uvw", - "body": { - "id": "chatcmpl-uvw", - "object": "chat.completion", - "model": "gemini-2.0-flash-001", - "choices": [ - { - "index": 0, - "message": {"role": "assistant", "content": "World!"}, - "finish_reason": "stop", - } - ], - "usage": { - "prompt_tokens": 8, - "completion_tokens": 3, - "total_tokens": 11, - }, - }, - }, - "error": None, - }, - ] - - original_flag = getattr( - litellm, "disable_vertex_batch_output_transformation", False - ) - try: - litellm.disable_vertex_batch_output_transformation = False - - result = await calculate_batch_cost_and_usage( - file_content_dictionary=openai_shaped_responses, - custom_llm_provider="vertex_ai", - model_name="gemini-2.0-flash-001", - ) - finally: - litellm.disable_vertex_batch_output_transformation = original_flag - - assert ( - result.usage.prompt_tokens == 18 - ), f"expected 18 prompt tokens, got {result.usage.prompt_tokens}" - assert ( - result.usage.completion_tokens == 8 - ), f"expected 8 completion tokens, got {result.usage.completion_tokens}" - assert ( - result.usage.total_tokens == 26 - ), f"expected 26 total tokens, got {result.usage.total_tokens}" - assert ( - result.cost > 0 - ), f"expected non-zero cost for completed Vertex batch, got {result.cost}" - - @pytest.mark.asyncio - async def test_raw_vertex_output_still_works_when_transformation_disabled(self): - """ - When disable_vertex_batch_output_transformation=True the GCS file is returned - as raw Vertex predictions.jsonl; the specialized reader must be used. - """ - import litellm - from litellm.batches.batch_utils import calculate_batch_cost_and_usage - - raw_vertex_responses = [ - { - "request": {"contents": [{"role": "user", "parts": [{"text": "hi"}]}]}, - "status": "", - "response": { - "candidates": [{"content": {"parts": [{"text": "Hello!"}]}}], - "usageMetadata": { - "promptTokenCount": 10, - "candidatesTokenCount": 5, - "totalTokenCount": 15, - }, - }, - "processed_time": "2026-01-01T00:00:00Z", - }, - ] - - original_flag = getattr( - litellm, "disable_vertex_batch_output_transformation", False - ) - try: - litellm.disable_vertex_batch_output_transformation = True - - result = await calculate_batch_cost_and_usage( - file_content_dictionary=raw_vertex_responses, - custom_llm_provider="vertex_ai", - model_name="gemini-2.0-flash-001", - ) - finally: - litellm.disable_vertex_batch_output_transformation = original_flag - - assert result.usage.prompt_tokens == 10 - assert result.usage.completion_tokens == 5 - assert result.usage.total_tokens == 15 - assert result.cost > 0, "raw Vertex shape should also produce non-zero cost" diff --git a/tests/test_litellm/proxy/spend_tracking/test_savings.py b/tests/test_litellm/proxy/spend_tracking/test_savings.py index 004f07da431..de413a86521 100644 --- a/tests/test_litellm/proxy/spend_tracking/test_savings.py +++ b/tests/test_litellm/proxy/spend_tracking/test_savings.py @@ -634,25 +634,6 @@ def test_equal_modeled_usage_is_zero_under_equivalent_model_names() -> None: assert _savings("claude-opus-5", "anthropic/claude-opus-5", usage, usage) == 0.0 -def test_baseline_is_priced_under_its_own_provider(): - """Two providers can serve the same bare model name at different rates, so dropping - the provider prices the baseline against a vendor the operator never named. Here it - decides whether routing reads as a saving or a loss.""" - usage = Usage(prompt_tokens=100_000, completion_tokens=10_000, total_tokens=110_000) - azure = compute_autorouter_savings( - baseline_model="azure_ai/deepseek-r1", - selected_model="claude-haiku-4-5", - selected_provider="anthropic", - usage=usage, - ) - deepseek = compute_autorouter_savings( - baseline_model="deepseek/deepseek-r1", - selected_model="claude-haiku-4-5", - selected_provider="anthropic", - usage=usage, - ) - assert azure != pytest.approx(deepseek) - assert azure > 0 > deepseek def test_unresolvable_baseline_remains_unknown(): diff --git a/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py b/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py index 16cbd109b24..e41c027d962 100644 --- a/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py +++ b/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py @@ -3887,179 +3887,7 @@ class TestSpendLogsPayload: } return mock_response - @pytest.mark.asyncio - async def test_spend_logs_payload_success_log_with_api_base(self, monkeypatch): - from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler - # Clear any env overrides that would change the recorded api_base - monkeypatch.delenv("ANTHROPIC_BASE_URL", raising=False) - monkeypatch.delenv("ANTHROPIC_API_BASE", raising=False) - - litellm.callbacks = [_ProxyDBLogger(message_logging=False)] - # litellm._turn_on_debug() - - client = AsyncHTTPHandler() - - with ( - patch.object( - litellm.proxy.db.db_spend_update_writer.DBSpendUpdateWriter, - "_insert_spend_log_to_db", - ) as mock_client, - patch.object(litellm.proxy.proxy_server, "prisma_client"), - patch.object(client, "post", side_effect=self.mock_anthropic_response), - ): - response = await litellm.acompletion( - model="claude-4-sonnet-20250514", - messages=[{"role": "user", "content": "Hello, world!"}], - metadata={"user_api_key_end_user_id": "test_user_1"}, - client=client, - ) - - assert response.choices[0].message.content == "Hi! My name is Claude." - - await _wait_for_mock_call(mock_client) - - kwargs = mock_client.call_args.kwargs - payload: SpendLogsPayload = kwargs["payload"] - expected_payload = SpendLogsPayload( - **{ - "request_id": "chatcmpl-34df56d5-4807-45c1-bb99-61e52586b802", - "call_type": "acompletion", - "api_key": "", - "cache_hit": "None", - "startTime": datetime.datetime( - 2025, 3, 24, 22, 2, 42, 975883, tzinfo=datetime.timezone.utc - ), - "endTime": datetime.datetime( - 2025, 3, 24, 22, 2, 42, 989132, tzinfo=datetime.timezone.utc - ), - "completionStartTime": datetime.datetime( - 2025, 3, 24, 22, 2, 42, 989132, tzinfo=datetime.timezone.utc - ), - "model": "claude-4-sonnet-20250514", - "user": "", - "team_id": "", - "metadata": '{"applied_guardrails": [], "attempted_fallbacks": null, "original_model_group": null, "batch_models": null, "batch_successful_requests": null, "batch_failed_requests": null, "mcp_tool_call_metadata": null, "vector_store_request_metadata": null, "routing_decision": null, "internal_call_origin": null, "guardrail_information": null, "compression_savings": null, "litellm_gateway_injected_cache": null, "router_metadata": null, "autorouter_savings_estimate": null, "autorouter_baseline_observation": null, "azure_spillover": null, "usage_object": {"completion_tokens": 503, "prompt_tokens": 2095, "total_tokens": 2598, "completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}, "model_map_information": {"model_map_key": "claude-4-sonnet-20250514", "model_map_value": {"key": "claude-4-sonnet-20250514", "max_tokens": 128000, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": null, "output_cost_per_token_batches": null, "output_cost_per_token": 1.5e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "anthropic", "mode": "chat", "supports_system_messages": null, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": true, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": false, "supports_reasoning": true, "search_context_cost_per_query": null, "tpm": null, "rpm": null, "supported_openai_params": ["stream", "stop", "temperature", "top_p", "max_tokens", "max_completion_tokens", "tools", "tool_choice", "extra_headers", "parallel_tool_calls", "response_format", "user", "reasoning_effort", "thinking"]}}, "additional_usage_values": {"completion_tokens_details": {"accepted_prediction_tokens": null, "audio_tokens": null, "reasoning_tokens": null, "rejected_prediction_tokens": null, "text_tokens": 503, "image_tokens": null}, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0, "text_tokens": null, "image_tokens": null}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}}', - "cache_key": "Cache OFF", - "spend": 0.01383, - "total_tokens": 2598, - "prompt_tokens": 2095, - "completion_tokens": 503, - "request_tags": "[]", - "end_user": "test_user_1", - "api_base": "https://api.anthropic.com/v1/messages", - "model_group": "", - "model_id": "", - "requester_ip_address": None, - "custom_llm_provider": "anthropic", - "messages": "{}", - "response": "{}", - "proxy_server_request": "{}", - "status": "success", - "mcp_namespaced_tool_name": None, - "agent_id": None, - } - ) - - differences = _compare_nested_dicts( - payload, expected_payload, ignore_keys=ignored_keys - ) - if differences: - pytest.fail(f"Dictionary mismatch: {differences}") - - @pytest.mark.asyncio - async def test_spend_logs_payload_success_log_with_router(self, monkeypatch): - from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler - - # Clear any env overrides that would change the recorded api_base - monkeypatch.delenv("ANTHROPIC_BASE_URL", raising=False) - monkeypatch.delenv("ANTHROPIC_API_BASE", raising=False) - - litellm.callbacks = [_ProxyDBLogger(message_logging=False)] - # litellm._turn_on_debug() - - client = AsyncHTTPHandler() - - router = Router( - model_list=[ - { - "model_name": "my-anthropic-model-group", - "litellm_params": { - "model": "claude-4-sonnet-20250514", - }, - "model_info": { - "id": "my-unique-model-id", - }, - } - ] - ) - - with ( - patch.object( - litellm.proxy.db.db_spend_update_writer.DBSpendUpdateWriter, - "_insert_spend_log_to_db", - ) as mock_client, - patch.object(litellm.proxy.proxy_server, "prisma_client"), - patch.object(client, "post", side_effect=self.mock_anthropic_response), - ): - response = await router.acompletion( - model="my-anthropic-model-group", - messages=[{"role": "user", "content": "Hello, world!"}], - metadata={"user_api_key_end_user_id": "test_user_1"}, - client=client, - ) - - assert response.choices[0].message.content == "Hi! My name is Claude." - - await _wait_for_mock_call(mock_client) - - kwargs = mock_client.call_args.kwargs - payload: SpendLogsPayload = kwargs["payload"] - expected_payload = SpendLogsPayload( - **{ - "request_id": "chatcmpl-34df56d5-4807-45c1-bb99-61e52586b802", - "call_type": "acompletion", - "api_key": "", - "cache_hit": "None", - "startTime": datetime.datetime( - 2025, 3, 24, 22, 2, 42, 975883, tzinfo=datetime.timezone.utc - ), - "endTime": datetime.datetime( - 2025, 3, 24, 22, 2, 42, 989132, tzinfo=datetime.timezone.utc - ), - "completionStartTime": datetime.datetime( - 2025, 3, 24, 22, 2, 42, 989132, tzinfo=datetime.timezone.utc - ), - "model": "claude-4-sonnet-20250514", - "user": "", - "team_id": "", - "metadata": '{"applied_guardrails": [], "attempted_fallbacks": 0, "original_model_group": "my-anthropic-model-group", "batch_models": null, "batch_successful_requests": null, "batch_failed_requests": null, "mcp_tool_call_metadata": null, "vector_store_request_metadata": null, "routing_decision": null, "internal_call_origin": null, "guardrail_information": null, "compression_savings": null, "litellm_gateway_injected_cache": null, "router_metadata": null, "autorouter_savings_estimate": null, "autorouter_baseline_observation": null, "azure_spillover": null, "usage_object": {"completion_tokens": 503, "prompt_tokens": 2095, "total_tokens": 2598, "completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}, "model_map_information": {"model_map_key": "claude-4-sonnet-20250514", "model_map_value": {"key": "claude-4-sonnet-20250514", "max_tokens": 128000, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": null, "output_cost_per_token_batches": null, "output_cost_per_token": 1.5e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "anthropic", "mode": "chat", "supports_system_messages": null, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": true, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": false, "supports_reasoning": true, "search_context_cost_per_query": null, "tpm": null, "rpm": null, "supported_openai_params": ["stream", "stop", "temperature", "top_p", "max_tokens", "max_completion_tokens", "tools", "tool_choice", "extra_headers", "parallel_tool_calls", "response_format", "user", "reasoning_effort", "thinking"]}}, "additional_usage_values": {"completion_tokens_details": {"accepted_prediction_tokens": null, "audio_tokens": null, "reasoning_tokens": null, "rejected_prediction_tokens": null, "text_tokens": 503, "image_tokens": null}, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0, "text_tokens": null, "image_tokens": null}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}}', - "cache_key": "Cache OFF", - "spend": 0.01383, - "total_tokens": 2598, - "prompt_tokens": 2095, - "completion_tokens": 503, - "request_tags": "[]", - "end_user": "test_user_1", - "api_base": "https://api.anthropic.com/v1/messages", - "model_group": "my-anthropic-model-group", - "model_id": "my-unique-model-id", - "requester_ip_address": None, - "custom_llm_provider": "anthropic", - "messages": "{}", - "response": "{}", - "proxy_server_request": "{}", - "status": "success", - "mcp_namespaced_tool_name": None, - "agent_id": None, - } - ) - - differences = _compare_nested_dicts( - payload, expected_payload, ignore_keys=ignored_keys - ) - if differences: - pytest.fail(f"Dictionary mismatch: {differences}") def _compare_nested_dicts( diff --git a/tests/test_litellm/responses/test_metadata_codex_callback.py b/tests/test_litellm/responses/test_metadata_codex_callback.py index f151f36be63..d5c411d63db 100644 --- a/tests/test_litellm/responses/test_metadata_codex_callback.py +++ b/tests/test_litellm/responses/test_metadata_codex_callback.py @@ -48,72 +48,6 @@ class MetadataCaptureCallback(CustomLogger): self.event.set() -@pytest.mark.asyncio -async def test_metadata_passed_to_custom_callback_codex_models(): - """ - Test that metadata passed to completion() is available in custom callback - when using codex models (responses API bridge path). - - Codex models have mode=responses and route through responses_api_bridge, - which passes litellm_metadata. The fix ensures this is preserved as - litellm_params.metadata for callback compatibility. - """ - from litellm.types.llms.openai import ResponsesAPIResponse - - mock_response = ResponsesAPIResponse.model_construct( - id="resp-test", - created_at=0, - output=[ - { - "type": "message", - "id": "msg-1", - "status": "completed", - "role": "assistant", - "content": [{"type": "output_text", "text": "Hello!"}], - } - ], - object="response", - model="gpt-5.1-codex", - status="completed", - usage={ - "input_tokens": 5, - "output_tokens": 10, - "total_tokens": 15, - }, - ) - - test_metadata = {"foo": "bar", "trace_id": "test-123"} - callback = MetadataCaptureCallback() - original_callbacks = litellm.callbacks.copy() if litellm.callbacks else [] - litellm.callbacks = [callback] - - try: - with patch( - "litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post", - new_callable=AsyncMock, - ) as mock_post: - mock_post.return_value = _make_mock_http_response( - mock_response.model_dump() - ) - # gpt-5.1-codex has mode=responses - routes through responses bridge - await litellm.acompletion( - model="gpt-5.1-codex", - messages=[{"role": "user", "content": "Hello"}], - metadata=test_metadata, - ) - - await asyncio.wait_for(callback.event.wait(), timeout=5.0) - - assert callback.captured_kwargs is not None, "Callback should have been invoked" - - litellm_params = callback.captured_kwargs.get("litellm_params", {}) - metadata = litellm_params.get("metadata") or {} - - assert "foo" in metadata, "metadata['foo'] should be accessible in callback" - assert metadata["foo"] == "bar" - assert metadata.get("trace_id") == "test-123" - finally: - litellm.callbacks = original_callbacks @pytest.mark.asyncio diff --git a/tests/test_litellm/rust_bridge/test_token_counter.py b/tests/test_litellm/rust_bridge/test_token_counter.py index 101fda629a7..3af7127a9b3 100644 --- a/tests/test_litellm/rust_bridge/test_token_counter.py +++ b/tests/test_litellm/rust_bridge/test_token_counter.py @@ -148,7 +148,6 @@ async def test_each_tokenizer_gets_its_own_cached_counter(fake_tokenizers: None) ("gpt-4o", "o200k_base"), ("gpt-4o-mini", "o200k_base"), ("gpt-4o-2024-08-06", "o200k_base"), - ("chatgpt-4o-latest", "o200k_base"), ("gpt-4.1", "o200k_base"), ("gpt-5", "o200k_base"), ("gpt-5-mini", "o200k_base"), diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index ecc01857f8c..e7ce9a74797 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -159,131 +159,8 @@ def test_cost_calculator_with_response_cost_in_additional_headers(): assert result == 1000 -def test_cost_calculator_with_usage(_local_model_cost_map, monkeypatch): - - usage = Usage( - prompt_tokens=120, - completion_tokens=100, - prompt_tokens_details=PromptTokensDetailsWrapper( - text_tokens=10, - audio_tokens=90, - image_tokens=20, - ), - ) - mr = ModelResponse(usage=usage, model="gemini-2.0-flash-001") - - result = response_cost_calculator( - response_object=mr, - model="", - custom_llm_provider="vertex_ai", - call_type="acompletion", - optional_params={}, - cache_hit=None, - base_model=None, - ) - - model_info = litellm.model_cost["gemini-2.0-flash-001"] - - # Step 1: Test a model where input_cost_per_image_token is not set. - # In this case the calculation should use input_cost_per_token as fallback. - assert model_info.get("input_cost_per_image_token") is None, ( - "Test case expects that input_cost_per_image_token is not set" - ) - - expected_cost = ( - usage.prompt_tokens_details.audio_tokens * model_info["input_cost_per_audio_token"] - + usage.prompt_tokens_details.text_tokens * model_info["input_cost_per_token"] - + usage.prompt_tokens_details.image_tokens * model_info["input_cost_per_token"] - + usage.completion_tokens * model_info["output_cost_per_token"] - ) - - assert result == expected_cost, f"Got {result}, Expected {expected_cost}" - - # Step 2: Set input_cost_per_image_token. - # In this case the explicit cost information should be used. - temp_model_info_object = dict(model_info) - temp_model_info_object["input_cost_per_image_token"] = 0.5 - - monkeypatch.setattr( - litellm, - "model_cost", - {"gemini-2.0-flash-001": temp_model_info_object}, - ) - - # Invalidate caches after modifying litellm.model_cost - from litellm.utils import _invalidate_model_cost_lowercase_map - - _invalidate_model_cost_lowercase_map() - - result = response_cost_calculator( - response_object=mr, - model="", - custom_llm_provider="vertex_ai", - call_type="acompletion", - optional_params={}, - cache_hit=None, - base_model=None, - ) - - expected_cost = ( - usage.prompt_tokens_details.audio_tokens * temp_model_info_object["input_cost_per_audio_token"] - + usage.prompt_tokens_details.text_tokens * temp_model_info_object["input_cost_per_token"] - + usage.prompt_tokens_details.image_tokens * temp_model_info_object["input_cost_per_image_token"] - + usage.completion_tokens * temp_model_info_object["output_cost_per_token"] - ) - - assert result == expected_cost, f"Got {result}, Expected {expected_cost}" -def test_handle_realtime_stream_cost_calculation_stores_cost_breakdown(): - """Regression: realtime cost must populate logging_obj.cost_breakdown so the - spend logs / UI show input vs output cost (issue: cost_breakdown was None for - /v1/realtime even though a total spend was computed).""" - from datetime import datetime - - from litellm.litellm_core_utils.litellm_logging import Logging - - results: OpenAIRealtimeStreamList = [ - {"type": "session.created", "session": {"model": "gpt-4o-realtime-preview"}}, - { - "type": "response.done", - "response": { - "usage": { - "input_tokens": 100, - "output_tokens": 50, - "total_tokens": 150, - } - }, - }, - ] - combined_usage_object = RealtimeAPITokenUsageProcessor.collect_and_combine_usage_from_realtime_stream_results( - results=results, - ) - - logging_obj = Logging( - model="gpt-4o-realtime-preview", - messages=[], - stream=False, - call_type="_arealtime", - start_time=datetime.now(), - litellm_call_id="realtime-cost-breakdown-test", - function_id="realtime-cost-breakdown-test", - ) - - total_cost = handle_realtime_stream_cost_calculation( - results=results, - combined_usage_object=combined_usage_object, - custom_llm_provider="openai", - litellm_model_name="gpt-4o-realtime-preview", - litellm_logging_obj=logging_obj, - ) - - assert total_cost > 0 - assert logging_obj.cost_breakdown is not None - assert logging_obj.cost_breakdown["input_cost"] > 0 - assert logging_obj.cost_breakdown["output_cost"] > 0 - assert abs(logging_obj.cost_breakdown["input_cost"] + logging_obj.cost_breakdown["output_cost"] - total_cost) < 1e-9 - assert abs(logging_obj.cost_breakdown["total_cost"] - total_cost) < 1e-9 def test_realtime_stream_combines_text_and_audio_token_details(): @@ -1124,126 +1001,6 @@ def test_bedrock_cost_calculator_comparison_with_without_cache(): print(f"Cost with cache: {cost_with_cache}") -def test_log_context_cost_calculation(): - """ - Test that log context cost calculation works correctly with tiered pricing. - - This test verifies that when using extended context (above 200k tokens), - the log context costs are calculated using the appropriate tiered rates. - """ - from litellm import completion_cost - from litellm.types.utils import ( - Choices, - Message, - ModelResponse, - PromptTokensDetailsWrapper, - Usage, - ) - - # Create a mock response with extended context usage - extended_context_response = ModelResponse( - id="test-extended-context-response", - created=1750733889, - model="claude-4-sonnet-20250514", - object="chat.completion", - system_fingerprint=None, - choices=[ - Choices( - finish_reason="stop", - index=0, - message=Message( - content="This is a test response for extended context cost calculation.", - role="assistant", - tool_calls=None, - function_call=None, - ), - ) - ], - usage=Usage( - total_tokens=350000, # Above 200k threshold - prompt_tokens=301000, # Above 200k threshold - completion_tokens=50000, - prompt_tokens_details=PromptTokensDetailsWrapper( - text_tokens=300000, - cached_tokens=0, # No cache hits - audio_tokens=None, - image_tokens=None, - character_count=None, - video_length_seconds=None, - cache_creation_tokens=1000, - ), - completion_tokens_details=None, - _cache_creation_input_tokens=1000, # Some tokens added to cache - ), - ) - - # Calculate the cost using the extended context model - result = completion_cost( - completion_response=extended_context_response, - model="claude-4-sonnet-20250514", - custom_llm_provider="anthropic", - ) - - # Debug: Print the actual result - print(f"DEBUG: Actual cost result: ${result:.6f}") - - # Get model info to understand the pricing - from litellm import get_model_info - - model_info = get_model_info(model="claude-4-sonnet-20250514", custom_llm_provider="anthropic") - - # Calculate expected cost based on actual model pricing - input_cost_per_token = model_info.get("input_cost_per_token", 0) - output_cost_per_token = model_info.get("output_cost_per_token", 0) - cache_creation_cost_per_token = model_info.get("cache_creation_input_token_cost", 0) - - # Check if tiered pricing is applied - input_cost_above_200k = model_info.get("input_cost_per_token_above_200k_tokens", input_cost_per_token) - output_cost_above_200k = model_info.get("output_cost_per_token_above_200k_tokens", output_cost_per_token) - cache_creation_above_200k = model_info.get( - "cache_creation_input_token_cost_above_200k_tokens", - cache_creation_cost_per_token, - ) - - print(f"DEBUG: Base input cost per token: ${input_cost_per_token:.2e}") - print(f"DEBUG: Base output cost per token: ${output_cost_per_token:.2e}") - print(f"DEBUG: Base cache creation cost per token: ${cache_creation_cost_per_token:.2e}") - - # Handle tiered pricing - if not available, use base pricing - if input_cost_above_200k is not None: - print(f"DEBUG: Tiered input cost per token (>200k): ${input_cost_above_200k:.2e}") - else: - print("DEBUG: No tiered input pricing available, using base pricing") - input_cost_above_200k = input_cost_per_token - - if output_cost_above_200k is not None: - print(f"DEBUG: Tiered output cost per token (>200k): ${output_cost_above_200k:.2e}") - else: - print("DEBUG: No tiered output pricing available, using base pricing") - output_cost_above_200k = output_cost_per_token - - if cache_creation_above_200k is not None: - print(f"DEBUG: Tiered cache creation cost per token (>200k): ${cache_creation_above_200k:.2e}") - else: - print("DEBUG: No tiered cache creation pricing available, using base pricing") - cache_creation_above_200k = cache_creation_cost_per_token - - # Since we're above 200k tokens, we should use tiered pricing if available - expected_input_cost = 300000 * input_cost_above_200k - expected_output_cost = 50000 * output_cost_above_200k - expected_cache_cost = 1000 * cache_creation_above_200k - expected_total = expected_input_cost + expected_output_cost + expected_cache_cost - - print(f"DEBUG: Expected total: ${expected_total:.6f}") - - # Allow for small floating point differences - assert abs(result - expected_total) < 1e-6, f"Expected cost ${expected_total:.6f}, but got ${result:.6f}" - - print(f"✓ Log context cost calculation with tiered pricing is correct: ${result:.6f}") - print(f" - Input tokens (300k): ${expected_input_cost:.6f}") - print(f" - Output tokens (50k): ${expected_output_cost:.6f}") - print(f" - Cache creation (1k): ${expected_cache_cost:.6f}") - print(f" - Total: ${result:.6f}") def test_gemini_25_explicit_caching_cost_direct_usage(): @@ -1814,56 +1571,6 @@ def test_cost_margin_with_discount(monkeypatch): print(f" - Expected: ${expected_cost:.6f}") -def test_azure_image_generation_cost_calculator(): - from unittest.mock import MagicMock - - from litellm.types.utils import ( - ImageObject, - ImageResponse, - ImageUsage, - ImageUsageInputTokensDetails, - ) - - response_cost_calculator_kwargs = { - "response_object": ImageResponse( - created=1761785270, - background=None, - data=[ - ImageObject( - b64_json=None, - revised_prompt="A futuristic, techno-inspired green duck wearing cool modern sunglasses. The duck has a sleek, metallic appearance with glowing neon green accents, standing on a high-tech urban background with holographic billboards and illuminated city lights in the distance. The duck's feathers have a glossy, high-tech sheen, resembling a robotic design but still maintaining its avian features. The scene has a vibrant, cyberpunk aesthetic with a neon color palette.", - url="test-azure-blob-url-with-sas-token", - ) - ], - output_format=None, - quality="hd", - size=None, - usage=ImageUsage( - input_tokens=0, - input_tokens_details=ImageUsageInputTokensDetails(image_tokens=0, text_tokens=0), - output_tokens=0, - total_tokens=0, - ), - ), - "model": "azure/dall-e-3", - "cache_hit": False, - "custom_llm_provider": "azure", - "base_model": "azure/dall-e-3", - "call_type": "aimage_generation", - "optional_params": {}, - "custom_pricing": False, - "prompt": "", - "standard_built_in_tools_params": { - "web_search_options": None, - "file_search": None, - }, - "router_model_id": "6738c432ffc9b733597c6b86613ca20dc5f49bde591fd3d03e7cd6aa25bb241e", - "litellm_logging_obj": MagicMock(), - "service_tier": None, - } - - cost = response_cost_calculator(**response_cost_calculator_kwargs) - assert cost > 0.079 def test_completion_cost_extracts_service_tier_from_response(_local_model_cost_map): @@ -2616,87 +2323,6 @@ def test_gemini_without_cache_tokens_details(): print("✅ Gemini without cacheTokensDetails works correctly") -def test_gemini_implicit_caching_cost_calculation(): - """ - Test for Issue #16341: Gemini implicit cached tokens not counted in spend log - - When Gemini uses implicit caching, it returns cachedContentTokenCount but NOT - cacheTokensDetails. In this case, we should subtract cachedContentTokenCount - from text_tokens to correctly calculate costs. - - See: https://github.com/BerriAI/litellm/issues/16341 - """ - from litellm import completion_cost - from litellm.llms.vertex_ai.gemini.vertex_and_google_ai_studio_gemini import ( - VertexGeminiConfig, - ) - from litellm.types.utils import Choices, Message, ModelResponse - - # Simulate Gemini response with implicit caching (cachedContentTokenCount only) - completion_response = { - "usageMetadata": { - "promptTokenCount": 10000, - "candidatesTokenCount": 5, - "totalTokenCount": 10005, - "cachedContentTokenCount": 8000, # Implicit caching - no cacheTokensDetails - "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10000}], - "candidatesTokensDetails": [{"modality": "TEXT", "tokenCount": 5}], - } - } - - usage = VertexGeminiConfig._calculate_usage(completion_response) - - # Verify parsing - assert usage.cache_read_input_tokens == 8000, ( - f"cache_read_input_tokens should be 8000, got {usage.cache_read_input_tokens}" - ) - assert usage.prompt_tokens_details.cached_tokens == 8000, ( - f"cached_tokens should be 8000, got {usage.prompt_tokens_details.cached_tokens}" - ) - - # CRITICAL: text_tokens should be (10000 - 8000) = 2000, NOT 10000 - # This is the fix for issue #16341 - assert usage.prompt_tokens_details.text_tokens == 2000, ( - f"text_tokens should be 2000 (10000 - 8000), got {usage.prompt_tokens_details.text_tokens}" - ) - - # Verify cost calculation uses cached token pricing - response = ModelResponse( - id="mock-id", - model="gemini-2.0-flash", - choices=[ - Choices( - index=0, - message=Message(role="assistant", content="Hello!"), - finish_reason="stop", - ) - ], - usage=usage, - ) - - cost = completion_cost( - completion_response=response, - model="gemini-2.0-flash", - custom_llm_provider="gemini", - ) - - # Get model pricing for verification - import litellm - - model_info = litellm.get_model_info("gemini/gemini-2.0-flash") - input_cost = model_info.get("input_cost_per_token", 0) - cache_read_cost = model_info.get("cache_read_input_token_cost", input_cost) - output_cost = model_info.get("output_cost_per_token", 0) - - # Expected cost: (2000 * input) + (8000 * cache_read) + (5 * output) - expected_cost = (2000 * input_cost) + (8000 * cache_read_cost) + (5 * output_cost) - - assert abs(cost - expected_cost) < 1e-9, ( - f"Cost calculation is wrong. Got ${cost:.6f}, expected ${expected_cost:.6f}. " - f"Cached tokens may not be using reduced pricing." - ) - - print("✅ Issue #16341 fix verified: Gemini implicit caching cost calculated correctly") def test_additional_costs_only_for_azure_ai(_local_model_cost_map): diff --git a/tests/test_litellm/test_count_tokens_public_api.py b/tests/test_litellm/test_count_tokens_public_api.py index 2918d0aa522..84121dd63e4 100644 --- a/tests/test_litellm/test_count_tokens_public_api.py +++ b/tests/test_litellm/test_count_tokens_public_api.py @@ -157,21 +157,3 @@ def test_acount_tokens_no_api_key_falls_back(monkeypatch): assert result.tokenizer_type == "local_tokenizer" -async def test_acount_tokens_local_fallback_counts_off_the_event_loop(): - from tests.large_text import text - from tests.test_litellm.litellm_core_utils.event_loop_lag import ( - assert_loop_stayed_free, - timed_with_loop_lags, - warm_tokenizer, - ) - - model = "together_ai/meta-llama/Llama-3-8b-chat-hf" - warm_tokenizer(model) - - result, took, lags = await timed_with_loop_lags( - lambda: litellm.acount_tokens(model=model, messages=[{"role": "user", "content": text * 100}]) - ) - - assert result.tokenizer_type == "local_tokenizer" - assert result.total_tokens > 100_000 - assert_loop_stayed_free(took, lags) diff --git a/tests/test_litellm/test_gpt_image_cost_calculator.py b/tests/test_litellm/test_gpt_image_cost_calculator.py index 0f471430daf..d026285f9ae 100644 --- a/tests/test_litellm/test_gpt_image_cost_calculator.py +++ b/tests/test_litellm/test_gpt_image_cost_calculator.py @@ -90,27 +90,6 @@ class TestGPTImageCostCalculator: class TestGPTImageCostRouting: """Test that gpt-image models are properly routed to the token-based calculator""" - def test_openai_dalle_routes_to_pixel_calculator(self): - """Test that OpenAI DALL-E still routes to pixel-based calculator""" - from litellm.litellm_core_utils.llm_cost_calc.utils import CostCalculatorUtils - - image_response = ImageResponse( - created=1234567890, - data=[ImageObject(url="http://example.com/image.jpg")], - ) - image_response.size = "1024x1024" - image_response.quality = "standard" - - cost = CostCalculatorUtils.route_image_generation_cost_calculator( - model="dall-e-3", - completion_response=image_response, - custom_llm_provider="openai", - size="1024x1024", - quality="standard", - n=1, - ) - - assert cost >= 0 class TestGPTImage15OutputImageTokens: diff --git a/tests/test_litellm/test_router.py b/tests/test_litellm/test_router.py index f5344c01f3a..411377f29cf 100644 --- a/tests/test_litellm/test_router.py +++ b/tests/test_litellm/test_router.py @@ -850,36 +850,6 @@ async def test_arouter_async_get_healthy_deployments(): assert result[0]["litellm_params"]["model"] == "gpt-3.5-turbo" -@pytest.mark.asyncio -@patch("litellm.amoderation") -async def test_arouter_amoderation_with_credential_name(mock_amoderation): - """ - Test that router.amoderation passes litellm_credential_name to the underlying litellm.amoderation call - """ - mock_amoderation.return_value = AsyncMock() - - router = litellm.Router( - model_list=[ - { - "model_name": "text-moderation-stable", - "litellm_params": { - "model": "text-moderation-stable", - "litellm_credential_name": "my-custom-auth", - }, - }, - ], - ) - - await router.amoderation(input="I love everyone!", model="text-moderation-stable") - - mock_amoderation.assert_called_once() - call_kwargs = mock_amoderation.call_args[1] # Get the kwargs of the call - print( - "call kwargs for router.amoderation=", - json.dumps(call_kwargs, indent=4, default=str), - ) - assert call_kwargs["litellm_credential_name"] == "my-custom-auth" - assert call_kwargs["model"] == "text-moderation-stable" def test_arouter_test_team_model(): diff --git a/tests/test_litellm/test_together_ai_model_metadata.py b/tests/test_litellm/test_together_ai_model_metadata.py index 7176ba4f219..dccba3d66f9 100644 --- a/tests/test_litellm/test_together_ai_model_metadata.py +++ b/tests/test_litellm/test_together_ai_model_metadata.py @@ -95,15 +95,6 @@ def _successor(info: dict[str, object]) -> str | None: return successor if isinstance(successor, str) else None -def test_together_successor_metadata_points_at_known_models(cost_map: CostMap): - successors = { - model: successor - for model, info in cost_map.items() - if model.startswith("together_ai/") and (successor := _successor(info)) is not None - } - assert len(successors) >= 10 - for model, successor in successors.items(): - assert successor in cost_map, f"{model} names successor {successor} that is not in the map" def test_together_backup_cost_map_in_sync(cost_map: CostMap): diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index ead805eed42..07982f51153 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -1465,12 +1465,6 @@ class TestProxyFunctionCalling: ("gemini/gemini-2.5-pro", "litellm_proxy/gemini/gemini-2.5-pro", True), ("gemini/gemini-2.5-flash", "litellm_proxy/gemini/gemini-2.5-flash", True), # Groq models (mixed support) - ("groq/gemma-7b-it", "litellm_proxy/groq/gemma-7b-it", True), - ( - "groq/llama-3.3-70b-versatile", - "litellm_proxy/groq/llama-3.3-70b-versatile", - True, - ), # Cohere models (generally don't support function calling) ("command-nightly", "litellm_proxy/command-nightly", False), ], diff --git a/tests/test_litellm/test_xai_responses_auto_routing.py b/tests/test_litellm/test_xai_responses_auto_routing.py index d405ea1e6c6..c31f599dd79 100644 --- a/tests/test_litellm/test_xai_responses_auto_routing.py +++ b/tests/test_litellm/test_xai_responses_auto_routing.py @@ -46,34 +46,6 @@ class TestXAIResponsesAutoRouting: assert model_info.get("mode") != "responses" assert updated_model == model - def test_responses_api_bridge_check_with_tools(self): - """Test that with tools, xAI automatically routes to Responses API""" - model = "grok-3" - custom_llm_provider = "xai" - tools = [ - { - "type": "function", - "function": { - "name": "get_weather", - "description": "Get the weather", - "parameters": { - "type": "object", - "properties": {"location": {"type": "string"}}, - }, - }, - } - ] - web_search_options = None - - model_info, updated_model = responses_api_bridge_check( - model=model, - custom_llm_provider=custom_llm_provider, - web_search_options=web_search_options, - ) - - # Should auto-route to responses mode when tools are present - assert model_info.get("mode") == "chat" - assert updated_model == model def test_responses_api_bridge_check_with_empty_tools(self): """Test that with empty tools list, xAI does not route to Responses API""" @@ -134,57 +106,8 @@ class TestXAIResponsesAutoRouting: assert model_info.get("mode") == "responses" assert updated_model == "grok-3" # prefix removed - def test_responses_api_bridge_check_with_code_interpreter_tool(self): - """Test auto-routing with code_interpreter tool""" - model = "grok-3" - custom_llm_provider = "xai" - tools = [{"type": "code_interpreter"}] - web_search_options = None - model_info, updated_model = responses_api_bridge_check( - model=model, - custom_llm_provider=custom_llm_provider, - web_search_options=web_search_options, - ) - # Should auto-route with code_interpreter tool - assert model_info.get("mode") == "chat" - assert updated_model == model - def test_responses_api_bridge_check_with_web_search_tool(self): - """Test auto-routing with web_search tool""" - model = "grok-4" - custom_llm_provider = "xai" - tools = [ - {"type": "web_search", "filters": {"allowed_domains": ["wikipedia.org"]}} - ] - web_search_options = None - - model_info, updated_model = responses_api_bridge_check( - model=model, - custom_llm_provider=custom_llm_provider, - web_search_options=web_search_options, - ) - - # Should auto-route with web_search tool - assert model_info.get("mode") == "chat" - assert updated_model == model - - def test_responses_api_bridge_check_with_x_search_tool(self): - """Test auto-routing with x_search tool""" - model = "grok-4" - custom_llm_provider = "xai" - tools = [{"type": "x_search", "allowed_x_handles": ["@elonmusk"]}] - web_search_options = None - - model_info, updated_model = responses_api_bridge_check( - model=model, - custom_llm_provider=custom_llm_provider, - web_search_options=web_search_options, - ) - - # Should auto-route with x_search tool - assert model_info.get("mode") == "chat" - assert updated_model == model def test_responses_api_bridge_check_with_web_search_options(self): """Test auto-routing with web_search_options""" diff --git a/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py b/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py index e4a33d5772c..47609261a25 100644 --- a/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py +++ b/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py @@ -157,27 +157,6 @@ def test_foundry_gpt_6_astra_keeps_sampling_params_when_reasoning_effort_is_none assert optional_params == {"reasoning_effort": "none", "temperature": 0.2, "top_p": 0.9} -def test_a_gpt_5_name_without_a_foundry_row_keeps_reading_its_own_entry( - monkeypatch: pytest.MonkeyPatch, _local_model_cost_map -): - """Most gpt-5-family names have no azure_ai/ row. Reading an azure_ai/ key for those finds - nothing, and an openai.azure.com base sends the name down the azure provider, which has no key - for it either, so every effort answer would silently fall back to false and take temperature, - top_p and logprobs down with it.""" - monkeypatch.setenv("AZURE_AI_API_BASE", "https://example-resource.openai.azure.com") - monkeypatch.setenv("AZURE_AI_API_KEY", "placeholder") - - optional_params = litellm.utils.get_optional_params( - model="gpt-5.1-chat-latest", - custom_llm_provider="azure_ai", - temperature=0.2, - top_p=0.9, - logprobs=True, - ) - - assert optional_params["temperature"] == 0.2 - assert optional_params["top_p"] == 0.9 - assert optional_params["logprobs"] is True def test_azure_ai_grok_stop_parameter_handling(): diff --git a/tests/unit/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py b/tests/unit/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py index 6815f00267c..3f740edf834 100644 --- a/tests/unit/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py +++ b/tests/unit/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py @@ -1695,21 +1695,6 @@ def test_nim_vllm_extras_translated_end_to_end_in_request_body(): assert request_body["top_k"] == 40 -def test_in_schema_unsupported_params_still_raise(): - with pytest.raises(litellm.UnsupportedParamsError): - litellm.get_optional_params( - model="accounts/fireworks/models/llama-v3-70b-instruct", - custom_llm_provider="fireworks_ai", - drop_params=False, - store=True, - ) - optional_params = litellm.get_optional_params( - model="accounts/fireworks/models/llama-v3-70b-instruct", - custom_llm_provider="fireworks_ai", - drop_params=True, - store=True, - ) - assert "store" not in optional_params def test_streaming_preserves_selected_model_for_private_accounting(): diff --git a/tests/unit/llms/moonshot/test_moonshot_chat_transformation.py b/tests/unit/llms/moonshot/test_moonshot_chat_transformation.py index c39affc18a8..4e7a2931cda 100644 --- a/tests/unit/llms/moonshot/test_moonshot_chat_transformation.py +++ b/tests/unit/llms/moonshot/test_moonshot_chat_transformation.py @@ -715,7 +715,7 @@ class TestMoonshotReasoningEffort: def force_local_model_cost(self, monkeypatch): monkeypatch.setattr(litellm, "model_cost", GetModelCostMap.load_local_model_cost_map()) - @pytest.mark.parametrize("model", ["kimi-k3", "kimi-k2.5", "kimi-k2.6", "kimi-k2-thinking"]) + @pytest.mark.parametrize("model", ["kimi-k3", "kimi-k2.5", "kimi-k2.6"]) def test_reasoning_model_supports_reasoning_effort(self, model): assert "reasoning_effort" in MoonshotChatConfig().get_supported_openai_params(model) From c37fe46534519c9be7f0a80a0f6786d154e6bbd7 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:20:18 -0700 Subject: [PATCH 08/11] test(vcr): guard leaked cassette patches and make injected-transport embedding tests immune (#42542) * test(vcr): guard leaked cassette patches and make injected-transport embedding tests immune * test(vcr): derive the leak guard's patch points from vcrpy's own reset list * test(vcr): share CapturingTransport and switch the encoding_format embedding test to it --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> --- tests/_vcr_conftest_common.py | 245 ++++++++++-------- tests/capturing_transport.py | 25 ++ tests/llm_translation/conftest.py | 30 ++- .../test_litellm_proxy_provider.py | 98 +++---- tests/llm_translation/test_nvidia_nim.py | 32 +-- tests/llm_translation/test_vcr_leak_guard.py | 72 +++++ tests/local_testing/conftest.py | 1 - tests/local_testing/test_embedding.py | 27 +- 8 files changed, 331 insertions(+), 199 deletions(-) create mode 100644 tests/capturing_transport.py create mode 100644 tests/llm_translation/test_vcr_leak_guard.py diff --git a/tests/_vcr_conftest_common.py b/tests/_vcr_conftest_common.py index 4d5a73779ea..ab046674eb6 100644 --- a/tests/_vcr_conftest_common.py +++ b/tests/_vcr_conftest_common.py @@ -8,6 +8,7 @@ from __future__ import annotations import ast import atexit import hashlib +import inspect import json import os import re @@ -15,10 +16,18 @@ import socket import sys import threading from collections import defaultdict -from typing import Iterable +from collections.abc import Iterable, Iterator +from contextlib import contextmanager +from dataclasses import dataclass +from pathlib import Path +from typing import Final +from unittest import mock +import aiohttp import pytest +import vcr import vcr.matchers as _vcr_matchers +import vcr.patch as _vcr_patch from tests._vcr_redis_persister import ( MAX_EPISODES_PER_CASSETTE, @@ -127,9 +136,7 @@ def emit_vcr_diagnostic_log(terminalreporter) -> None: with open(path, "r", encoding="utf-8") as fh: content = fh.read() except OSError as exc: - read_errors.append( - f" [failed to read {name}: {type(exc).__name__}: {exc}]" - ) + read_errors.append(f" [failed to read {name}: {type(exc).__name__}: {exc}]") continue for line in content.splitlines(): if not line.strip(): @@ -142,9 +149,7 @@ def emit_vcr_diagnostic_log(terminalreporter) -> None: return terminalreporter.write_sep("=", "VCR DIAGNOSTIC LOG", bold=True) - terminalreporter.write_line( - f" source dir: {directory} (deduplicated; full log archived as a CI artifact)" - ) + terminalreporter.write_line(f" source dir: {directory} (deduplicated; full log archived as a CI artifact)") for line in read_errors: terminalreporter.write_line(line) @@ -235,9 +240,7 @@ def pin_httpx_multipart_boundary(monkeypatch) -> None: boundary = VCR_FIXED_MULTIPART_BOUNDARY.encode("ascii") return _original_init(self, data=data, files=files, boundary=boundary, **kwargs) - monkeypatch.setattr( - _httpx_multipart.MultipartStream, "__init__", _init_with_fixed_boundary - ) + monkeypatch.setattr(_httpx_multipart.MultipartStream, "__init__", _init_with_fixed_boundary) @pytest.fixture(scope="session", autouse=True) @@ -270,11 +273,7 @@ def _replace_b64_json_in_place(obj) -> bool: changed = False if isinstance(obj, dict): for key, value in obj.items(): - if ( - key == "b64_json" - and isinstance(value, str) - and len(value) > len(VCR_IMAGE_B64_PLACEHOLDER) - ): + if key == "b64_json" and isinstance(value, str) and len(value) > len(VCR_IMAGE_B64_PLACEHOLDER): obj[key] = VCR_IMAGE_B64_PLACEHOLDER changed = True elif _replace_b64_json_in_place(value): @@ -296,16 +295,12 @@ def _strip_image_b64_payloads(response): preserves all those checks while shrinking cassettes by ~99%. """ if not isinstance(response, dict): - vcr_diag_write_line( - f"[vcr-strip-b64] response is {type(response).__name__!r}, not " - "dict; skipping b64 scrub" - ) + vcr_diag_write_line(f"[vcr-strip-b64] response is {type(response).__name__!r}, not dict; skipping b64 scrub") return response body = response.get("body") if not isinstance(body, dict): vcr_diag_write_line( - f"[vcr-strip-b64] response['body'] is {type(body).__name__!r}, " - "not dict; skipping b64 scrub" + f"[vcr-strip-b64] response['body'] is {type(body).__name__!r}, not dict; skipping b64 scrub" ) return response raw = body.get("string") @@ -316,10 +311,7 @@ def _strip_image_b64_payloads(response): try: text = bytes(raw).decode("utf-8") except UnicodeDecodeError: - vcr_diag_write_line( - "[vcr-strip-b64] response body bytes are not valid UTF-8; " - "skipping b64 scrub" - ) + vcr_diag_write_line("[vcr-strip-b64] response body bytes are not valid UTF-8; skipping b64 scrub") return response was_bytes = True elif isinstance(raw, str): @@ -327,8 +319,7 @@ def _strip_image_b64_payloads(response): was_bytes = False else: vcr_diag_write_line( - f"[vcr-strip-b64] response['body']['string'] is " - f"{type(raw).__name__!r}, not bytes/str; skipping b64 scrub" + f"[vcr-strip-b64] response['body']['string'] is {type(raw).__name__!r}, not bytes/str; skipping b64 scrub" ) return response @@ -349,9 +340,7 @@ def _strip_image_b64_payloads(response): for key in list(headers): if str(key).lower() == "content-length": value = headers[key] - headers[key] = ( - [new_len_value] if isinstance(value, list) else new_len_value - ) + headers[key] = [new_len_value] if isinstance(value, list) else new_len_value return response @@ -409,15 +398,11 @@ def _canonical_body(request) -> tuple[bytes, str]: # selected. This mirrors the existing SigV4 / multipart-boundary / b64-image # normalizations already in this module, and means the already-bloated # cassettes start replaying immediately without a flush + re-record. -_VCR_UUID_RE = re.compile( - rb"[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}" -) +_VCR_UUID_RE = re.compile(rb"[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}") _VCR_LITELLM_BATCH_JOB_RE = re.compile(rb"litellm-batch-[0-9a-fA-F]{8}") # ISO-8601 timestamps, e.g. ``2026-05-25T03:40:37.262045Z`` / # ``2026-05-25T03:40:37+00:00``. -_VCR_ISO_TS_RE = re.compile( - rb"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:?\d{2})?" -) +_VCR_ISO_TS_RE = re.compile(rb"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:?\d{2})?") # Unix epoch as 13-digit milliseconds, then 10-digit ``time.time()`` float, # then 10-digit integer seconds. Anchored to ``1`` + 9/12 digits, which keeps # them inside the 2001-2033 / 2001-2033 epoch windows and avoids matching @@ -639,10 +624,7 @@ def _should_drop_telemetry_record(request) -> bool: return False if not _is_telemetry_request(request): return False - if ( - _is_telemetry_export_request(request) - and not _current_test_replays_telemetry_export() - ): + if _is_telemetry_export_request(request) and not _current_test_replays_telemetry_export(): return True return not _current_test_records_telemetry() @@ -767,9 +749,7 @@ def _iter_header_values(headers, name: str): yield value -_AWS_SIGV4_CREDENTIAL_RE = re.compile( - r"AWS4-HMAC-SHA256\s+Credential=([^/\s,]+)/", re.IGNORECASE -) +_AWS_SIGV4_CREDENTIAL_RE = re.compile(r"AWS4-HMAC-SHA256\s+Credential=([^/\s,]+)/", re.IGNORECASE) # Google OAuth2 access tokens always start with ``ya29.`` regardless of how # they were minted (service account, metadata server, impersonation). @@ -891,9 +871,7 @@ def _normalize_multipart_boundary(request) -> None: return try: - headers[content_type_key] = content_type_value.replace( - match.group(0), fixed_param - ) + headers[content_type_key] = content_type_value.replace(match.group(0), fixed_param) except (TypeError, AttributeError): return @@ -985,8 +963,7 @@ def _materialize_iterable_body(request) -> None: uri = getattr(request, "uri", getattr(request, "url", "?")) first_type = type(chunks[0]).__name__ if chunks else "empty" vcr_diag_write_line( - f"[vcr-materialize] FALLBACK: {method} {uri} chunk type " - f"{first_type!r} not coerced to bytes; storing b''" + f"[vcr-materialize] FALLBACK: {method} {uri} chunk type {first_type!r} not coerced to bytes; storing b''" ) out = b"" @@ -1026,9 +1003,7 @@ def _key_fingerprint_matcher(r1, r2) -> None: return def _fp(req): - for value in _iter_header_values( - getattr(req, "headers", None), KEY_FINGERPRINT_HEADER - ): + for value in _iter_header_values(getattr(req, "headers", None), KEY_FINGERPRINT_HEADER): if value is None: continue return value if isinstance(value, str) else str(value) @@ -1159,13 +1134,11 @@ def _print_atexit_banner() -> None: _emit("VCR CASSETTE CACHE DEGRADED") if save_failures: _emit( - f" {save_failures} cassette save failure(s); last error: " - f"{health.get('save_failure_last_error', '')}" + f" {save_failures} cassette save failure(s); last error: {health.get('save_failure_last_error', '')}" ) if load_failures: _emit( - f" {load_failures} cassette load failure(s); last error: " - f"{health.get('load_failure_last_error', '')}" + f" {load_failures} cassette load failure(s); last error: {health.get('load_failure_last_error', '')}" ) if snapshot: _emit(_format_capacity_line(snapshot)) @@ -1276,11 +1249,7 @@ class _RespxUsageVisitor(ast.NodeVisitor): if isinstance(dec, ast.Call): dec = dec.func if isinstance(dec, ast.Attribute): - return ( - isinstance(dec.value, ast.Name) - and dec.value.id == "respx" - and dec.attr == "mock" - ) + return isinstance(dec.value, ast.Name) and dec.value.id == "respx" and dec.attr == "mock" return False def _is_pytest_mark_respx(self, dec: ast.expr) -> bool: @@ -1307,9 +1276,7 @@ class _RespxUsageVisitor(ast.NodeVisitor): # ``def test_foo(respx_mock): ...`` — pytest supplies the fixture # whenever the parameter name appears, regardless of marker. all_args = ( - list(args.args) - + list(args.kwonlyargs) - + (list(args.posonlyargs) if hasattr(args, "posonlyargs") else []) + list(args.args) + list(args.kwonlyargs) + (list(args.posonlyargs) if hasattr(args, "posonlyargs") else []) ) for a in all_args: if a.arg == "respx_mock": @@ -1566,9 +1533,7 @@ def _emit_outcome_payload( }, ) ) - node.user_properties.append( - (_USER_PROP_RECORDED_BY, os.environ.get("PYTEST_XDIST_WORKER", "")) - ) + node.user_properties.append((_USER_PROP_RECORDED_BY, os.environ.get("PYTEST_XDIST_WORKER", ""))) def aggregate_report_outcome(report) -> None: @@ -1616,9 +1581,7 @@ def aggregate_report_outcome(report) -> None: if verdict == VERDICT_MISS_OVERFLOW: _session_stats["overflow_tests"].append(nodeid) elif verdict == VERDICT_UNMARKED_LIVE_CALL: - _session_stats["unmarked_live_call_tests"].append( - (nodeid, list(outcome.get("live_call_hosts") or [])) - ) + _session_stats["unmarked_live_call_tests"].append((nodeid, list(outcome.get("live_call_hosts") or []))) skip_reason = outcome.get("skip_reason") if skip_reason: @@ -1635,9 +1598,7 @@ def session_stats_snapshot() -> dict: "overflow_tests": list(_session_stats["overflow_tests"]), "unmarked_live_call_tests": list(_session_stats["unmarked_live_call_tests"]), "skip_reason_counts": dict(_session_stats["skip_reason_counts"]), - "skip_reason_examples": { - k: list(v) for k, v in _session_stats["skip_reason_examples"].items() - }, + "skip_reason_examples": {k: list(v) for k, v in _session_stats["skip_reason_examples"].items()}, } @@ -1810,9 +1771,7 @@ def record_vcr_outcome(request, vcr) -> None: # Cassette is None ⇒ test wasn't VCR-marked. Honor the skip reason # we tagged at collection time, and pull live-call hosts captured by # the socket probe (if any). - skip_reason = getattr( - request.node, VCR_SKIP_REASON_USER_ATTR, SKIP_REASON_FILE_OPT_OUT - ) + skip_reason = getattr(request.node, VCR_SKIP_REASON_USER_ATTR, SKIP_REASON_FILE_OPT_OUT) _session_stats["skip_reason_counts"][skip_reason] += 1 hosts = getattr(request.node, _LIVE_CALL_BUFFER_KEY, []) or [] @@ -1837,9 +1796,7 @@ def record_vcr_outcome(request, vcr) -> None: live_call_hosts=hosts, ) if vcr_outcome_logging_enabled(): - request.node.user_properties.append( - (_USER_PROP_VERDICT_LINE, _format_verdict_line(verdict, None, extra)) - ) + request.node.user_properties.append((_USER_PROP_VERDICT_LINE, _format_verdict_line(verdict, None, extra))) def install_live_call_probe(request, vcr) -> None: @@ -1858,9 +1815,7 @@ def install_live_call_probe(request, vcr) -> None: # Track the current test for telemetry-leak suppression (applies to every # test, VCR-marked or not). See ``_should_drop_telemetry_record``. global _current_test_nodeid - _current_test_nodeid = str( - getattr(getattr(request, "node", None), "nodeid", "") or "" - ) + _current_test_nodeid = str(getattr(getattr(request, "node", None), "nodeid", "") or "") if vcr is not None or vcr_disabled(): return None probe = _LiveCallProbe() @@ -1876,10 +1831,7 @@ def _format_capacity_line(snapshot: dict) -> str: pct = float(snapshot.get("used_pct", 0.0) or 0.0) used_mb = used / (1024 * 1024) cap_mb = cap / (1024 * 1024) - return ( - f" Cassette Redis usage: {used_mb:.1f} MiB / {cap_mb:.1f} MiB " - f"({pct:.1f}% of maxmemory)" - ) + return f" Cassette Redis usage: {used_mb:.1f} MiB / {cap_mb:.1f} MiB ({pct:.1f}% of maxmemory)" def emit_vcr_classification_summary(terminalreporter) -> None: @@ -1940,14 +1892,10 @@ def emit_vcr_classification_summary(terminalreporter) -> None: total_leaks = sum(leak_counts.values()) terminalreporter.write_sep("-", "VCR COST LEAK CHECK", bold=True) if total_leaks: - rendered = ", ".join( - f"{verdict}={count}" for verdict, count in leak_counts.items() if count - ) + rendered = ", ".join(f"{verdict}={count}" for verdict, count in leak_counts.items() if count) terminalreporter.write_line(f" FAIL: {rendered}") else: - terminalreporter.write_line( - " PASS: no overflow, partial, not-persisted, or unmarked live-call verdicts" - ) + terminalreporter.write_line(" PASS: no overflow, partial, not-persisted, or unmarked live-call verdicts") overflow = snapshot["overflow_tests"] if overflow: @@ -2007,18 +1955,14 @@ def emit_cassette_cache_session_banner(terminalreporter) -> None: snapshot = cassette_cache_capacity_snapshot() if save_failures or load_failures: - terminalreporter.write_sep( - "=", "VCR CASSETTE CACHE DEGRADED", red=True, bold=True - ) + terminalreporter.write_sep("=", "VCR CASSETTE CACHE DEGRADED", red=True, bold=True) if save_failures: terminalreporter.write_line( - f" {save_failures} cassette save failure(s); last error: " - f"{health.get('save_failure_last_error', '')}" + f" {save_failures} cassette save failure(s); last error: {health.get('save_failure_last_error', '')}" ) if load_failures: terminalreporter.write_line( - f" {load_failures} cassette load failure(s); last error: " - f"{health.get('load_failure_last_error', '')}" + f" {load_failures} cassette load failure(s); last error: {health.get('load_failure_last_error', '')}" ) terminalreporter.write_line( " Tests still passed because cassette persistence is best-effort, " @@ -2031,9 +1975,7 @@ def emit_cassette_cache_session_banner(terminalreporter) -> None: return if snapshot and snapshot["used_pct"] >= CASSETTE_CACHE_HIGH_WATER_FRACTION * 100: - terminalreporter.write_sep( - "=", "VCR CASSETTE CACHE NEAR CAPACITY", yellow=True, bold=True - ) + terminalreporter.write_sep("=", "VCR CASSETTE CACHE NEAR CAPACITY", yellow=True, bold=True) terminalreporter.write_line(_format_capacity_line(snapshot)) terminalreporter.write_line( " No save failures yet, but Redis is approaching maxmemory. " @@ -2082,13 +2024,104 @@ class VerboseReporterState: if reporter is None: return verdict = next( - ( - v - for k, v in (report.user_properties or []) - if k == _USER_PROP_VERDICT_LINE - ), + (v for k, v in (report.user_properties or []) if k == _USER_PROP_VERDICT_LINE), None, ) if not verdict: return reporter.write_line(f"{verdict} :: {report.nodeid}") + + +@dataclass(frozen=True, slots=True) +class VcrPatchPoint: + owner: object + attribute: str + original: object + + @property + def name(self) -> str: + return f"{_patch_owner_name(self.owner)}.{self.attribute}" + + def current(self) -> object: + current: Final[object] = getattr(self.owner, self.attribute) + return current + + def is_patched(self) -> bool: + return self.current() is not self.original + + def restore(self) -> None: + setattr(self.owner, self.attribute, self.original) + + +def _patch_owner_name(owner: object) -> str: + if inspect.isclass(owner): + return f"{owner.__module__}.{owner.__qualname__}" + if inspect.ismodule(owner): + return owner.__name__ + return repr(owner) + + +def _vcr_patch_point(patcher: mock._patch[object]) -> VcrPatchPoint: + owner: Final[object] = patcher.getter() + return VcrPatchPoint(owner=owner, attribute=patcher.attribute, original=patcher.new) + + +_VCR_PATCH_POINTS: Final = ( + *(_vcr_patch_point(patcher) for patcher in _vcr_patch.reset_patchers()), + VcrPatchPoint(aiohttp.ClientSession, "_request", _vcr_patch._AiohttpClientSessionRequest), +) + + +@dataclass(frozen=True, slots=True) +class VcrPatchLeak: + patch_points: tuple[str, ...] + cassette_paths: tuple[str, ...] + + +def _cassette_paths_wrapped_into(fn: object) -> tuple[str, ...]: + if not inspect.isfunction(fn): + return () + cassette: Final = inspect.getclosurevars(fn).nonlocals.get("cassette") + own: Final = (str(cassette._path),) if isinstance(cassette, vcr.cassette.Cassette) else () + return own + _cassette_paths_wrapped_into(getattr(fn, "__wrapped__", None)) + + +def detect_vcr_patch_leak() -> VcrPatchLeak | None: + leaked: Final = tuple(point for point in _VCR_PATCH_POINTS if point.is_patched()) + if not leaked: + return None + return VcrPatchLeak( + patch_points=tuple(point.name for point in leaked), + cassette_paths=tuple( + dict.fromkeys(path for point in leaked for path in _cassette_paths_wrapped_into(point.current())) + ), + ) + + +def restore_vcr_patch_points() -> None: + for point in _VCR_PATCH_POINTS: + point.restore() + + +def guard_vcr_patch_points(item: pytest.Item, teardown_failed: bool) -> None: + leak: Final = detect_vcr_patch_leak() + if leak is None: + return + restore_vcr_patch_points() + if teardown_failed: + return + pytest.fail( + f"{item.nodeid} finished with a vcrpy cassette still patched into " + f"{', '.join(leak.patch_points)} (cassettes: {', '.join(leak.cassette_paths) or 'unknown'}); " + "the originals were restored so later tests are unaffected", + pytrace=False, + ) + + +@contextmanager +def rewound_new_episodes_cassette(cassette_dir: Path) -> Iterator[vcr.cassette.Cassette]: + cassette_path: Final = cassette_dir / "rewound_owner.yaml" + cassette_path.write_text("interactions: []\nversion: 1\n") + recorder: Final = vcr.VCR(cassette_library_dir=str(cassette_dir)) + with recorder.use_cassette(cassette_path.name, record_mode="new_episodes") as cassette: + yield cassette diff --git a/tests/capturing_transport.py b/tests/capturing_transport.py new file mode 100644 index 00000000000..496c286685c --- /dev/null +++ b/tests/capturing_transport.py @@ -0,0 +1,25 @@ +from __future__ import annotations + +from collections.abc import Mapping +from typing import Final + +import httpx +from pydantic import BaseModel, TypeAdapter + +_JSON_OBJECT: Final = TypeAdapter(Mapping[str, object]) + + +class CapturingTransport(httpx.AsyncBaseTransport, httpx.BaseTransport): + def __init__(self, response: BaseModel) -> None: + self._response: Final = response + self.request_bodies: tuple[Mapping[str, object], ...] = () + + def handle_request(self, request: httpx.Request) -> httpx.Response: + return self._respond(request.read()) + + async def handle_async_request(self, request: httpx.Request) -> httpx.Response: + return self._respond(await request.aread()) + + def _respond(self, body: bytes) -> httpx.Response: + self.request_bodies = (*self.request_bodies, _JSON_OBJECT.validate_json(body)) + return httpx.Response(200, json=self._response.model_dump(mode="json")) diff --git a/tests/llm_translation/conftest.py b/tests/llm_translation/conftest.py index 567040c1d19..a88dcf4ae3e 100644 --- a/tests/llm_translation/conftest.py +++ b/tests/llm_translation/conftest.py @@ -7,6 +7,8 @@ import asyncio import importlib +from collections.abc import Generator +from typing import Final import pytest @@ -20,6 +22,7 @@ from tests._vcr_conftest_common import ( # noqa: E402,F401 emit_cassette_cache_session_banner, emit_vcr_classification_summary, emit_vcr_diagnostic_log, + guard_vcr_patch_points, install_live_call_probe, record_vcr_outcome, register_persister_if_enabled, @@ -37,17 +40,12 @@ def fake_openai_endpoint(): # Per-item respx detection (``apply_vcr_auto_marker_to_items``) handles # the vast majority of respx-vs-vcrpy conflicts automatically. The entries -# below are the persister's and the WebSocket VCR's own unit-test files, which -# exercise ``save_cassette`` / ``load_cassette`` against fakeredis and must not -# themselves run under a live cassette context. +# below are the persister's, the WebSocket VCR's, and the cassette patch-leak +# guard's own unit-test files, which exercise ``save_cassette`` / +# ``load_cassette`` against fakeredis or enter cassettes themselves and must +# not run under a live cassette context. _VCR_AUTO_MARKER_SKIP_FILES = frozenset( - {"test_vcr_redis_persister.py", "test_ws_vcr.py"} -) - -_VCR_INCOMPATIBLE_NODEID_SUFFIXES: tuple[str, ...] = ( - "test_nvidia_nim.py::test_embedding_nvidia_nim", - "test_litellm_proxy_provider.py::test_litellm_gateway_from_sdk_embedding[False]", - "test_litellm_proxy_provider.py::test_litellm_gateway_from_sdk_embedding[True]", + {"test_vcr_redis_persister.py", "test_ws_vcr.py", "test_vcr_leak_guard.py"} ) @@ -77,6 +75,17 @@ def _vcr_outcome_gate(request, vcr): record_vcr_outcome(request, vcr) +@pytest.hookimpl(wrapper=True, trylast=True) +def pytest_runtest_teardown(item: pytest.Item) -> Generator[None, object, object]: + try: + result: Final = yield + except BaseException: + guard_vcr_patch_points(item, teardown_failed=True) + raise + guard_vcr_patch_points(item, teardown_failed=False) + return result + + def pytest_configure(config): _verbose_state.remember_pluginmanager(config) reset_vcr_diag_dir() @@ -172,7 +181,6 @@ def pytest_collection_modifyitems(config, items): apply_vcr_auto_marker_to_items( items, skip_files=_VCR_AUTO_MARKER_SKIP_FILES, - skip_nodeid_suffixes=_VCR_INCOMPATIBLE_NODEID_SUFFIXES, ) custom_logger_tests = [ diff --git a/tests/llm_translation/test_litellm_proxy_provider.py b/tests/llm_translation/test_litellm_proxy_provider.py index 8630259877d..a10fc55ecc5 100644 --- a/tests/llm_translation/test_litellm_proxy_provider.py +++ b/tests/llm_translation/test_litellm_proxy_provider.py @@ -2,6 +2,8 @@ import json import re from datetime import datetime from io import BytesIO +from pathlib import Path +from typing import Final from unittest.mock import AsyncMock @@ -12,7 +14,12 @@ import pytest from unittest.mock import MagicMock, patch from litellm.llms.custom_httpx.http_handler import HTTPHandler, AsyncHTTPHandler import pytest_asyncio -from openai import AsyncOpenAI +from openai import AsyncOpenAI, OpenAI +from openai.types import CreateEmbeddingResponse, Embedding +from openai.types.create_embedding_response import Usage + +from tests.capturing_transport import CapturingTransport +from tests._vcr_conftest_common import rewound_new_episodes_cassette @pytest.mark.asyncio @@ -87,62 +94,61 @@ async def test_litellm_gateway_from_sdk_structured_output(): assert "json_schema" in json_schema -@pytest.mark.parametrize("is_async", [False, True]) +_GATEWAY_EMBEDDING_RESPONSE: Final = CreateEmbeddingResponse( + object="list", + data=(Embedding(object="embedding", index=0, embedding=(0.1, 0.2, 0.3)),), + model="my-vllm-model", + usage=Usage(prompt_tokens=2, total_tokens=2), +) + + +async def _gateway_embedding_via_injected_client( + is_async: bool, +) -> tuple[CapturingTransport, litellm.EmbeddingResponse]: + transport: Final = CapturingTransport(_GATEWAY_EMBEDDING_RESPONSE) + response: Final = ( + await litellm.aembedding( + model="litellm_proxy/my-vllm-model", + input="Hello world", + client=AsyncOpenAI(api_key="fake-key", http_client=httpx.AsyncClient(transport=transport)), + api_base="my-custom-api-base", + ) + if is_async + else litellm.embedding( + model="litellm_proxy/my-vllm-model", + input="Hello world", + client=OpenAI(api_key="fake-key", http_client=httpx.Client(transport=transport)), + api_base="my-custom-api-base", + ) + ) + return transport, response + + +@pytest.mark.parametrize("is_async", (False, True)) @pytest.mark.asyncio -async def test_litellm_gateway_from_sdk_embedding(is_async): +async def test_litellm_gateway_from_sdk_embedding(is_async: bool): litellm.set_verbose = True litellm._turn_on_debug() - captured_bodies = [] - - def handler(request: httpx.Request) -> httpx.Response: - captured_bodies.append(json.loads(request.content)) - return httpx.Response( - 200, - json={ - "object": "list", - "data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}], - "model": "my-vllm-model", - "usage": {"prompt_tokens": 2, "total_tokens": 2}, - }, - ) - - if is_async: - from openai import AsyncOpenAI - - openai_client = AsyncOpenAI( - api_key="fake-key", - http_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)), - ) - response = await litellm.aembedding( - model="litellm_proxy/my-vllm-model", - input="Hello world", - client=openai_client, - api_base="my-custom-api-base", - ) - else: - from openai import OpenAI - - openai_client = OpenAI( - api_key="fake-key", - http_client=httpx.Client(transport=httpx.MockTransport(handler)), - ) - response = litellm.embedding( - model="litellm_proxy/my-vllm-model", - input="Hello world", - client=openai_client, - api_base="my-custom-api-base", - ) - - request_body = captured_bodies[0] - print("Request body - {}".format(request_body)) + transport, response = await _gateway_embedding_via_injected_client(is_async) + request_body: Final = transport.request_bodies[0] assert "Hello world" == request_body["input"] assert "my-vllm-model" == request_body["model"] assert "encoding_format" not in request_body assert response.data[0]["embedding"] == [0.1, 0.2, 0.3] +@pytest.mark.asyncio +async def test_litellm_gateway_from_sdk_embedding_under_foreign_cassette(tmp_path: Path): + with rewound_new_episodes_cassette(tmp_path): + sync_transport, _ = await _gateway_embedding_via_injected_client(is_async=False) + async_transport, _ = await _gateway_embedding_via_injected_client(is_async=True) + + assert tuple(body["input"] for body in sync_transport.request_bodies) == ("Hello world",) + assert tuple(body["input"] for body in async_transport.request_bodies) == ("Hello world",) + + @pytest.mark.parametrize("is_async", [False, True]) @pytest.mark.asyncio async def test_litellm_gateway_from_sdk_image_generation(is_async): diff --git a/tests/llm_translation/test_nvidia_nim.py b/tests/llm_translation/test_nvidia_nim.py index d5942e674d0..0f16c01fd2f 100644 --- a/tests/llm_translation/test_nvidia_nim.py +++ b/tests/llm_translation/test_nvidia_nim.py @@ -1,17 +1,21 @@ import json from datetime import datetime +from typing import Final from unittest.mock import AsyncMock import httpx import pytest +from openai.types import CreateEmbeddingResponse, Embedding +from openai.types.create_embedding_response import Usage as EmbeddingUsage from unittest.mock import patch, MagicMock import litellm from litellm import Choices, Message, ModelResponse, EmbeddingResponse, Usage from litellm import completion from base_rerank_unit_tests import BaseLLMRerankTest +from tests.capturing_transport import CapturingTransport def test_completion_nvidia_nim(): @@ -63,33 +67,23 @@ def test_embedding_nvidia_nim(): litellm.set_verbose = True from openai import OpenAI - captured_bodies = [] - - def handler(request: httpx.Request) -> httpx.Response: - captured_bodies.append(json.loads(request.content)) - return httpx.Response( - 200, - json={ - "object": "list", - "data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}], - "model": "nvidia/nv-embedqa-e5-v5", - "usage": {"prompt_tokens": 6, "total_tokens": 6}, - }, + transport: Final = CapturingTransport( + CreateEmbeddingResponse( + object="list", + data=(Embedding(object="embedding", index=0, embedding=(0.1, 0.2, 0.3)),), + model="nvidia/nv-embedqa-e5-v5", + usage=EmbeddingUsage(prompt_tokens=6, total_tokens=6), ) - - client = OpenAI( - api_key="fake-api-key", - http_client=httpx.Client(transport=httpx.MockTransport(handler)), ) - response = litellm.embedding( + client: Final = OpenAI(api_key="fake-api-key", http_client=httpx.Client(transport=transport)) + response: Final = litellm.embedding( model="nvidia_nim/nvidia/nv-embedqa-e5-v5", input="What is the meaning of life?", input_type="passage", dimensions=1024, client=client, ) - request_body = captured_bodies[0] - print("request_body: ", request_body) + request_body: Final = transport.request_bodies[0] assert request_body["input"] == "What is the meaning of life?" assert request_body["model"] == "nvidia/nv-embedqa-e5-v5" assert request_body["input_type"] == "passage" diff --git a/tests/llm_translation/test_vcr_leak_guard.py b/tests/llm_translation/test_vcr_leak_guard.py new file mode 100644 index 00000000000..5372342790b --- /dev/null +++ b/tests/llm_translation/test_vcr_leak_guard.py @@ -0,0 +1,72 @@ +from __future__ import annotations + +import re +from pathlib import Path +from typing import Final + +import httpx +import httpx2 +import pytest + +from tests._vcr_conftest_common import ( + detect_vcr_patch_leak, + guard_vcr_patch_points, + restore_vcr_patch_points, + rewound_new_episodes_cassette, +) + +_ORIGINAL_MOCK_HANDLE_ASYNC_REQUEST: Final = httpx.MockTransport.handle_async_request +_ORIGINAL_HTTPX2_MOCK_HANDLE_ASYNC_REQUEST: Final = httpx2.MockTransport.handle_async_request + + +@pytest.fixture +def leaked_cassette_dir(tmp_path: Path): + context: Final = rewound_new_episodes_cassette(tmp_path) + context.__enter__() + yield tmp_path + context.__exit__(None, None, None) + + +def test_no_leak_when_no_cassette_is_active(): + assert detect_vcr_patch_leak() is None + + +def test_leaked_cassette_is_detected_named_and_restorable(leaked_cassette_dir: Path): + leak: Final = detect_vcr_patch_leak() + + assert leak is not None + assert {"httpx.MockTransport.handle_async_request", "aiohttp.client.ClientSession._request"} <= set( + leak.patch_points + ) + assert leak.cassette_paths == (str(leaked_cassette_dir / "rewound_owner.yaml"),) + + restore_vcr_patch_points() + + assert detect_vcr_patch_leak() is None + assert httpx.MockTransport.handle_async_request is _ORIGINAL_MOCK_HANDLE_ASYNC_REQUEST + + +def test_leak_is_detected_on_every_transport_family_vcrpy_patches(leaked_cassette_dir: Path): + leak: Final = detect_vcr_patch_leak() + + assert leak is not None + assert "httpx2.MockTransport.handle_async_request" in leak.patch_points + assert httpx2.MockTransport.handle_async_request is not _ORIGINAL_HTTPX2_MOCK_HANDLE_ASYNC_REQUEST + + restore_vcr_patch_points() + + assert httpx2.MockTransport.handle_async_request is _ORIGINAL_HTTPX2_MOCK_HANDLE_ASYNC_REQUEST + + +def test_guard_fails_the_leaking_test_and_restores_the_originals(request, leaked_cassette_dir: Path): + with pytest.raises(pytest.fail.Exception, match=re.escape(request.node.nodeid)) as failure: + guard_vcr_patch_points(request.node, teardown_failed=False) + + assert str(leaked_cassette_dir / "rewound_owner.yaml") in str(failure.value) + assert detect_vcr_patch_leak() is None + + +def test_guard_restores_silently_when_the_teardown_already_failed(request, leaked_cassette_dir: Path): + guard_vcr_patch_points(request.node, teardown_failed=True) + + assert detect_vcr_patch_leak() is None diff --git a/tests/local_testing/conftest.py b/tests/local_testing/conftest.py index 228457f4d55..d03f074f557 100644 --- a/tests/local_testing/conftest.py +++ b/tests/local_testing/conftest.py @@ -93,7 +93,6 @@ _VCR_INCOMPATIBLE_FILES = frozenset( # carry no real provider cost. _VCR_INCOMPATIBLE_NODEID_SUFFIXES: tuple[str, ...] = ( "test_router.py::test_router_text_completion_client", - "test_embedding.py::test_encoding_format_omitted_by_default_for_openai_sdk", ) diff --git a/tests/local_testing/test_embedding.py b/tests/local_testing/test_embedding.py index c119334da6f..acbc4f20405 100644 --- a/tests/local_testing/test_embedding.py +++ b/tests/local_testing/test_embedding.py @@ -15,6 +15,9 @@ from unittest.mock import AsyncMock, MagicMock, patch import litellm from litellm import completion, completion_cost, embedding +from openai.types import CreateEmbeddingResponse +from openai.types.create_embedding_response import Usage as EmbeddingUsage +from tests.capturing_transport import CapturingTransport from tests.fake_openai_endpoint import FAKE_OPENAI_API_BASE litellm.set_verbose = False @@ -1268,23 +1271,15 @@ def test_encoding_format_omitted_by_default_for_openai_sdk(monkeypatch): Optional global override: `LITELLM_DEFAULT_EMBEDDING_ENCODING_FORMAT`. """ monkeypatch.delenv("LITELLM_DEFAULT_EMBEDDING_ENCODING_FORMAT", raising=False) - captured_bodies = [] - - def handler(request: httpx.Request) -> httpx.Response: - captured_bodies.append(json.loads(request.content)) - return httpx.Response( - 200, - json={ - "object": "list", - "data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}], - "model": "text-embedding-ada-002", - "usage": {"prompt_tokens": 1, "total_tokens": 1}, - }, + transport = CapturingTransport( + CreateEmbeddingResponse( + object="list", + data=(Embedding(object="embedding", index=0, embedding=(0.1, 0.2, 0.3)),), + model="text-embedding-ada-002", + usage=EmbeddingUsage(prompt_tokens=1, total_tokens=1), ) - - client = openai.OpenAI( - api_key="sk-test", http_client=httpx.Client(transport=httpx.MockTransport(handler)) ) + client = openai.OpenAI(api_key="sk-test", http_client=httpx.Client(transport=transport)) response = embedding( model="text-embedding-ada-002", @@ -1294,7 +1289,7 @@ def test_encoding_format_omitted_by_default_for_openai_sdk(monkeypatch): ) assert response.data[0]["embedding"] == [0.1, 0.2, 0.3] - assert "encoding_format" not in captured_bodies[0], ( + assert "encoding_format" not in transport.request_bodies[0], ( "encoding_format should be omitted from the upstream request when not provided by user" ) From 676486886178dc83de9c3e489ca047af882a652d Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:24:32 -0700 Subject: [PATCH 09/11] fix(otel): keep text completion choice fields beside the synthesized message (#42537) Co-authored-by: yucheng Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/integrations/otel/model/payloads.py | 8 +- tests/integration/contracts.json | 3 + .../test_otel_text_completion_choices.py | 110 ++++++++++++++++++ .../otel/test_otel_v2_sources_of_truth.py | 23 +++- 4 files changed, 142 insertions(+), 2 deletions(-) create mode 100644 tests/integration/observability/test_otel_text_completion_choices.py diff --git a/litellm/integrations/otel/model/payloads.py b/litellm/integrations/otel/model/payloads.py index 240107251c5..2f337c59148 100644 --- a/litellm/integrations/otel/model/payloads.py +++ b/litellm/integrations/otel/model/payloads.py @@ -776,9 +776,15 @@ def _joined_choice(parts: tuple[str, ...]) -> tuple[_Choice, ...]: return (_text_choice("\n\n".join(parts)),) if parts else () +def _text_completion_choice(choice: Mapping[str, object], text: str) -> Mapping[str, object]: + synthesized: Final = _text_choice(text, as_str(choice.get("finish_reason"))) + merged: Final = (*choice.items(), *synthesized.items()) + return {k: v for k, v in merged if k != "text"} # mutable-ok: mappers json.dumps and isinstance(dict) it + + def _completion_choices(response: Mapping[str, object]) -> tuple[Mapping[str, object], ...]: return tuple( - _text_choice(text, as_str(choice.get("finish_reason"))) + _text_completion_choice(choice, text) if "message" not in choice and isinstance(text := choice.get("text"), str) else choice for choice in _dicts(response.get("choices")) diff --git a/tests/integration/contracts.json b/tests/integration/contracts.json index d12e3ae4620..cdf534bb5a1 100644 --- a/tests/integration/contracts.json +++ b/tests/integration/contracts.json @@ -248,6 +248,9 @@ "other.observability.callbacks.credentials_stay_out_of_event_bodies", "other.observability.callbacks.concurrent_results_join_complete_events_and_rows" ], + "tests/integration/observability/test_otel_text_completion_choices.py::test_otel_weave_output_keeps_text_completion_provider_fields_beside_the_synthesized_message": [ + "other.observability.otel.text_completion_choices_keep_provider_fields" + ], "tests/integration/observability/test_guardrail_effects.py::test_guardrail_rewrites_system_and_user_in_actual_anthropic_request": [ "other.observability.guardrails.rewrite_reaches_correct_anthropic_positions" ], diff --git a/tests/integration/observability/test_otel_text_completion_choices.py b/tests/integration/observability/test_otel_text_completion_choices.py new file mode 100644 index 00000000000..70c104a61aa --- /dev/null +++ b/tests/integration/observability/test_otel_text_completion_choices.py @@ -0,0 +1,110 @@ +import json +import uuid +from pathlib import Path +from typing import Final + +import pytest +import yaml + +from integration._support.client import Gateway, eventually +from integration._support.process import owned_proxy +from integration._support.wire import Reply, Request, wire_server + + +def _span_attributes(body: bytes) -> tuple[dict[str, object], ...]: + return tuple( + {attribute["key"]: attribute["value"] for attribute in span.get("attributes", ())} + for resource in json.loads(body)["resourceSpans"] + for scope in resource["scopeSpans"] + for span in scope["spans"] + ) + + +@pytest.mark.covers("other.observability.otel.text_completion_choices_keep_provider_fields") +def test_otel_weave_output_keeps_text_completion_provider_fields_beside_the_synthesized_message( + gateway: Gateway, tmp_path: Path +) -> None: + marker: Final = "otel-text-" + uuid.uuid4().hex + logprobs: Final = { + "tokens": ["Hello", " there"], + "token_logprobs": [-0.1, -0.2], + "top_logprobs": None, + "text_offset": [0, 5], + } + content_filter: Final = {"hate": {"filtered": False, "severity": "safe"}} + + def upstream(request: Request) -> Reply: + assert request.target.endswith("/completions"), request.target + return Reply( + body=json.dumps( + { + "id": marker, + "object": "text_completion", + "created": 1, + "model": "gpt-3.5-turbo-instruct", + "choices": [ + { + "index": 0, + "text": "Hello there", + "finish_reason": "stop", + "logprobs": logprobs, + "content_filter_results": content_filter, + } + ], + "usage": {"prompt_tokens": 3, "completion_tokens": 2, "total_tokens": 5}, + } + ).encode() + ) + + def sink(_request: Request) -> Reply: + return Reply() + + with wire_server(upstream) as provider, wire_server(sink) as collector: + config: Final = yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()) + config["litellm_settings"].update({"callbacks": ["otel"]}) + config["callback_settings"] = { + "otel": { + "exporter": "http/json", + "endpoint": collector.url, + "mapper_names": ["genai", "openinference", "weave"], + "capture_message_content": "span_only", + "use_simple_processor": True, + } + } + path: Final = tmp_path / "otel.yaml" + path.write_text(yaml.safe_dump(config)) + with ( + owned_proxy(gateway, tmp_path, {"LITELLM_OTEL_V2": "1"}, config=path) as candidate, + candidate.scenario() as scenario, + ): + model: Final = scenario.model(model="openai/gpt-3.5-turbo-instruct", api_base=provider.url + "/v1") + response: Final = candidate.request( + "POST", "/v1/completions", {"model": model, "prompt": marker, "cache": {"no-cache": True}} + ) + assert response.status_code == 200, response.text + assert response.json()["choices"][0]["text"] == "Hello there" + batches = [] + + def outputs() -> tuple[list[dict[str, object]], ...]: + batches.extend(collector.drain()) + return tuple( + json.loads(attributes["weave.output"]["stringValue"]) + for batch in batches + for attributes in _span_attributes(batch.body) + if "weave.output" in attributes + and attributes.get("gen_ai.response.id", {}).get("stringValue") == marker + ) + + choices: Final = eventually(outputs, lambda values: len(values) == 1, seconds=20)[0] + assert len(choices) == 1, choices + choice: Final = choices[0] + assert choice["message"]["content"] == "Hello there", choice + assert "text" not in choice, choice + assert { + key: choice.get(key) for key in ("index", "finish_reason", "logprobs", "content_filter_results") + } == { + "index": 0, + "finish_reason": "stop", + "logprobs": logprobs, + "content_filter_results": content_filter, + }, choice diff --git a/tests/test_litellm/integrations/otel/test_otel_v2_sources_of_truth.py b/tests/test_litellm/integrations/otel/test_otel_v2_sources_of_truth.py index b9ec625fdfc..95df3709ab8 100644 --- a/tests/test_litellm/integrations/otel/test_otel_v2_sources_of_truth.py +++ b/tests/test_litellm/integrations/otel/test_otel_v2_sources_of_truth.py @@ -934,11 +934,32 @@ def test_text_completion_choices_become_assistant_messages_in_choice_order() -> capture_content=True, ) - assert data.choices_out == (_assistant_choice(" first", "length"), _assistant_choice(" second", "stop")) + assert data.choices_out == ( + {"index": 0, "logprobs": None, **_assistant_choice(" first", "length")}, + {"index": 1, "logprobs": None, **_assistant_choice(" second", "stop")}, + ) assert data.finish_reasons == ("length", "stop") assert data.response_id == "cmpl-1" +def test_text_completion_choices_keep_provider_fields_beside_the_synthesized_message() -> None: + choice: Final = { + "index": 2, + "text": "Hello there", + "finish_reason": "stop", + "logprobs": {"tokens": ["Hello"], "token_logprobs": [-0.1]}, + "content_filter_results": {"hate": {"filtered": False}}, + "provider_specific": {"cached": True}, + } + data: Final = LLMCallSpanData.from_standard_logging_payload( + _route_payload("atext_completion", "gpt-3.5-turbo-instruct", {"choices": [choice]}), capture_content=True + ) + + assert data.choices_out == ( + {k: v for k, v in choice.items() if k != "text"} | _assistant_choice("Hello there", "stop"), + ) + + def test_text_completion_choices_follow_the_content_capture_gate_but_finish_reasons_do_not() -> None: data: Final = LLMCallSpanData.from_standard_logging_payload( _route_payload( From b277be0867abaa11a29815d73ed7d5a66962cf1e Mon Sep 17 00:00:00 2001 From: joshua-berri Date: Tue, 22 Sep 2026 21:26:48 +0000 Subject: [PATCH 10/11] fix(mcp): preserve discovery attribution and sanitize logging headers (#42541) Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com> --- .../proxy/_experimental/mcp_server/utils.py | 6 +-- litellm/proxy/litellm_pre_call_utils.py | 9 +++- litellm/responses/main.py | 19 ++++----- .../responses/mcp/chat_completions_handler.py | 1 + .../mcp/litellm_proxy_mcp_handler.py | 4 ++ .../_experimental/mcp_server/test_utils.py | 6 +-- .../proxy/test_litellm_pre_call_utils.py | 42 +++++++++++++++++++ .../mcp/test_chat_completions_handler.py | 1 + .../mcp/test_litellm_proxy_mcp_handler.py | 40 +++++++++++++++++- 9 files changed, 109 insertions(+), 19 deletions(-) diff --git a/litellm/proxy/_experimental/mcp_server/utils.py b/litellm/proxy/_experimental/mcp_server/utils.py index 6bd080f5216..7411dc5c4f0 100644 --- a/litellm/proxy/_experimental/mcp_server/utils.py +++ b/litellm/proxy/_experimental/mcp_server/utils.py @@ -986,7 +986,7 @@ def _forwarded_upstream_header_names() -> frozenset[str]: ) -def _upstream_credential_headers(header_names: Iterable[str]) -> frozenset[str]: +def upstream_credential_headers(header_names: Iterable[str]) -> frozenset[str]: """Lowercased names of the headers in ``header_names`` that carry an upstream MCP credential rather than request context: the configured client side auth header, any header name a configured server forwards upstream via ``extra_headers``, and the @@ -1038,7 +1038,7 @@ def build_synthetic_mcp_request( custom_key_header: Final = _custom_litellm_key_header_name() excluded: Final = ( _SYNTHETIC_REQUEST_EXCLUDED_HEADERS - | _upstream_credential_headers(raw_headers.keys() if raw_headers else ()) + | upstream_credential_headers(raw_headers.keys() if raw_headers else ()) | (frozenset({custom_key_header.lower()}) if custom_key_header else frozenset()) ) forwarded: Final = tuple( @@ -1086,7 +1086,7 @@ def logging_safe_mcp_headers(raw_headers: Mapping[str, str] | None) -> Mapping[s ) excluded: Final = ( - _upstream_credential_headers(raw_headers.keys() if raw_headers else ()) + upstream_credential_headers(raw_headers.keys() if raw_headers else ()) | UNTRUSTED_REQUEST_HEADER_CONTROL_FIELDS | frozenset({"host"}) ) diff --git a/litellm/proxy/litellm_pre_call_utils.py b/litellm/proxy/litellm_pre_call_utils.py index 4d5b91be034..90bba82aa84 100644 --- a/litellm/proxy/litellm_pre_call_utils.py +++ b/litellm/proxy/litellm_pre_call_utils.py @@ -2029,7 +2029,14 @@ async def add_litellm_data_to_request( _headers, allow_client_message_redaction_opt_out=_allow_client_message_redaction_opt_out, ) - _logging_safe_headers: Final = redact_credential_headers(_headers) + from litellm.proxy._experimental.mcp_server.utils import upstream_credential_headers + + _mcp_credential_headers: Final = upstream_credential_headers(_headers) + _logging_safe_headers: Final = redact_credential_headers( + MappingProxyType( + {name: value for name, value in _headers.items() if name.lower() not in _mcp_credential_headers} + ) + ) verbose_proxy_logger.debug("Request Headers: %s", _logging_safe_headers) verbose_proxy_logger.debug("Raw Headers: %s", _raw_headers) diff --git a/litellm/responses/main.py b/litellm/responses/main.py index 5c4c9ea3987..e771cdf5ae4 100644 --- a/litellm/responses/main.py +++ b/litellm/responses/main.py @@ -209,16 +209,12 @@ async def aresponses_api_with_mcp( user_api_key_auth = kwargs.get("user_api_key_auth") or kwargs.get("litellm_metadata", {}).get("user_api_key_auth") # Extract MCP auth headers from request (for dynamic auth when fetching tools) - mcp_auth_header: str | None = None - mcp_server_auth_headers: dict[str, dict[str, str]] | None = None - secret_fields = kwargs.get("secret_fields") - if secret_fields and isinstance(secret_fields, dict): - ( - mcp_auth_header, - mcp_server_auth_headers, - _, - _, - ) = ResponsesAPIRequestUtils.extract_mcp_headers_from_request(secret_fields=secret_fields, tools=tools) + secret_fields: Final = kwargs.get("secret_fields") + mcp_auth_header, mcp_server_auth_headers, _, discovery_raw_headers = ( + ResponsesAPIRequestUtils.extract_mcp_headers_from_request(secret_fields=secret_fields, tools=tools) + if isinstance(secret_fields, dict) and secret_fields + else (None, None, None, None) + ) # Get original MCP tools (for events) and OpenAI tools (for LLM) by reusing existing methods ( @@ -231,6 +227,7 @@ async def aresponses_api_with_mcp( mcp_auth_header=mcp_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, request_tags=LiteLLM_Proxy_MCP_Handler._get_parent_request_tags(kwargs), + raw_headers=discovery_raw_headers, ) openai_tools: Final = LiteLLM_Proxy_MCP_Handler._transform_mcp_tools_to_openai(original_mcp_tools) @@ -330,7 +327,6 @@ async def aresponses_api_with_mcp( user_api_key_auth = kwargs.get("litellm_metadata", {}).get("user_api_key_auth") # Extract MCP auth headers from the request to pass to MCP server - secret_fields = kwargs.get("secret_fields") ( mcp_auth_header, mcp_server_auth_headers, @@ -416,6 +412,7 @@ async def aresponses_api_with_mcp( mcp_auth_header=mcp_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, request_tags=LiteLLM_Proxy_MCP_Handler._get_parent_request_tags(kwargs), + raw_headers=discovery_raw_headers, ) final_response = LiteLLM_Proxy_MCP_Handler._add_mcp_output_elements_to_response( response=final_response, diff --git a/litellm/responses/mcp/chat_completions_handler.py b/litellm/responses/mcp/chat_completions_handler.py index df1e3e62441..b17e0befba6 100644 --- a/litellm/responses/mcp/chat_completions_handler.py +++ b/litellm/responses/mcp/chat_completions_handler.py @@ -138,6 +138,7 @@ async def acompletion_with_mcp( mcp_auth_header=mcp_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, request_tags=request_tags, + raw_headers=raw_headers, ) openai_tools: Final = LiteLLM_Proxy_MCP_Handler._transform_mcp_tools_to_openai( diff --git a/litellm/responses/mcp/litellm_proxy_mcp_handler.py b/litellm/responses/mcp/litellm_proxy_mcp_handler.py index 319f10a9b22..71f61079154 100644 --- a/litellm/responses/mcp/litellm_proxy_mcp_handler.py +++ b/litellm/responses/mcp/litellm_proxy_mcp_handler.py @@ -236,6 +236,7 @@ class LiteLLM_Proxy_MCP_Handler: mcp_auth_header: str | None = None, mcp_server_auth_headers: dict[str, dict[str, str]] | None = None, request_tags: list[str] | None = None, + raw_headers: dict[str, str] | None = None, ) -> tuple[list[MCPTool], list[str]]: """ Get available tools from the MCP server manager. @@ -326,6 +327,7 @@ class LiteLLM_Proxy_MCP_Handler: list_tools_log_source="responses", litellm_trace_id=litellm_trace_id, request_tags=request_tags, + raw_headers=raw_headers, ) tools: Final = listing.tools @@ -452,6 +454,7 @@ class LiteLLM_Proxy_MCP_Handler: mcp_auth_header: str | None = None, mcp_server_auth_headers: dict[str, dict[str, str]] | None = None, request_tags: list[str] | None = None, + raw_headers: dict[str, str] | None = None, ) -> tuple[list[MCPTool], dict[str, str]]: """ Process MCP tools through filtering and deduplication pipeline without OpenAI transformation. @@ -482,6 +485,7 @@ class LiteLLM_Proxy_MCP_Handler: mcp_auth_header=mcp_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, request_tags=request_tags, + raw_headers=raw_headers, ) # Step 2: Filter tools based on allowed_tools parameter diff --git a/tests/test_litellm/proxy/_experimental/mcp_server/test_utils.py b/tests/test_litellm/proxy/_experimental/mcp_server/test_utils.py index 842859e5a1e..8d10219796b 100644 --- a/tests/test_litellm/proxy/_experimental/mcp_server/test_utils.py +++ b/tests/test_litellm/proxy/_experimental/mcp_server/test_utils.py @@ -4,7 +4,7 @@ import pytest from fastapi import HTTPException from litellm.proxy._experimental.mcp_server.utils import ( - _upstream_credential_headers, + upstream_credential_headers, build_synthetic_mcp_request, logging_safe_mcp_headers, validate_and_normalize_mcp_server_payload, @@ -189,8 +189,8 @@ class TestLoggingSafeMcpHeaders: """clean_headers already strips authorization, and claiming it here would change which header authenticated_with_header resolves to on a config that lists it by design.""" with _configured_servers(_server_forwarding("Authorization", "X-GitHub-Token")): - assert "authorization" not in _upstream_credential_headers(["authorization", "x-github-token"]) - assert "x-github-token" in _upstream_credential_headers(["authorization", "x-github-token"]) + assert "authorization" not in upstream_credential_headers(["authorization", "x-github-token"]) + assert "x-github-token" in upstream_credential_headers(["authorization", "x-github-token"]) def test_keeps_headers_when_no_server_forwards_them(self): with _configured_servers(_server_forwarding("x-github-token")): diff --git a/tests/test_litellm/proxy/test_litellm_pre_call_utils.py b/tests/test_litellm/proxy/test_litellm_pre_call_utils.py index b7b7b5d1942..8fb53d4b0a0 100644 --- a/tests/test_litellm/proxy/test_litellm_pre_call_utils.py +++ b/tests/test_litellm/proxy/test_litellm_pre_call_utils.py @@ -8238,3 +8238,45 @@ def test_default_team_settings_bool_turn_off_message_logging_redacts(): ) is True ) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("path", ["/mcp-rest/tools/call", "/v1/responses", "/v1/chat/completions"]) +@pytest.mark.parametrize("custom_auth", ["x-mcp-auth", "x-private-mcp-token"]) +async def test_mcp_credentials_only_removed_from_logging_copies(path: str, custom_auth: str): + from litellm.types.mcp_server.mcp_server_manager import MCPServer + + metadata_name: Final = "litellm_metadata" if path == "/v1/responses" else "metadata" + secrets: Final = { + "X-MCP-Deepwiki-Authorization": "upstream-sentinel", + custom_auth: "client-auth-sentinel", + "x-service-token": "configured-secret-sentinel", + } + attribution: Final = {"x-app-id": "app-a", "x-nuid": "user-a", "x-user-id": "identity-a"} + request: Final = _make_request_mock(path, {"Content-Type": "application/json", **secrets, **attribution}) + request.headers = Headers(request.headers) + settings: Final = {"mcp_client_side_auth_header_name": custom_auth, "user_header_name": "x-user-id"} + server: Final = MCPServer( + server_id="header-test", name="header-test", transport="http", url="https://example.com/mcp", + extra_headers=["x-service-token", "x-user-id"], + ) + with ( + patch("litellm.proxy.proxy_server.general_settings", settings), + patch.dict( + "litellm.proxy._experimental.mcp_server.mcp_server_manager.global_mcp_server_manager.config_mcp_servers", + {"header-test": server}, clear=True, + ), + ): + updated: Final = await add_litellm_data_to_request( + data={"model": "test-model", "messages": [{"role": "user", "content": "hello"}]}, + request=request, user_api_key_dict=UserAPIKeyAuth(api_key="hashed-key"), + proxy_config=MagicMock(), general_settings=settings, version="test", + ) + for header_dict in _all_header_dicts(updated, metadata_name): + assert not any(value in json.dumps(header_dict) for value in secrets.values()) + assert updated[metadata_name]["headers"] == updated["proxy_server_request"]["headers"] + for name, value in attribution.items(): + assert updated[metadata_name]["headers"][name] == value + for name, value in secrets.items(): + assert updated["secret_fields"]["raw_headers"][name.lower()] == value + assert request.headers[name] == value diff --git a/tests/test_litellm/responses/mcp/test_chat_completions_handler.py b/tests/test_litellm/responses/mcp/test_chat_completions_handler.py index 6e049d7634c..54e98cc2b6c 100644 --- a/tests/test_litellm/responses/mcp/test_chat_completions_handler.py +++ b/tests/test_litellm/responses/mcp/test_chat_completions_handler.py @@ -159,6 +159,7 @@ async def test_acompletion_with_mcp_passes_mcp_server_auth_headers_to_process_to secret_fields=secret_fields, ) + assert captured_process_kwargs["raw_headers"] == secret_fields["raw_headers"] assert "mcp_server_auth_headers" in captured_process_kwargs mcp_server_auth_headers = captured_process_kwargs["mcp_server_auth_headers"] assert mcp_server_auth_headers is not None diff --git a/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py b/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py index 56e40206ebe..57cebf489a2 100644 --- a/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py +++ b/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py @@ -3,7 +3,7 @@ import subprocess import sys import textwrap import types -from typing import Any, cast +from typing import Any, Final, cast from unittest.mock import AsyncMock, MagicMock import pytest @@ -1226,6 +1226,7 @@ async def test_mcp_follow_up_call_is_stateless_when_store_is_false( ) async def fake_process(**kwargs: Any) -> tuple[list[Any], dict[str, str]]: + assert kwargs["raw_headers"] == {"x-app-id": "follow-up-caller"} return ([], {"foo": "litellm_proxy"}) async def fake_execute(**kwargs: Any) -> list[dict[str, Any]]: @@ -1245,6 +1246,7 @@ async def test_mcp_follow_up_call_is_stateless_when_store_is_false( model="gpt-5", tools=[{"type": "mcp", "server_url": "litellm_proxy", "require_approval": "never"}], litellm_metadata={"guardrails": ["block-all"]}, + secret_fields={"raw_headers": {"x-app-id": "follow-up-caller"}}, store=store, previous_response_id=caller_previous_response_id, ) @@ -1257,3 +1259,39 @@ async def test_mcp_follow_up_call_is_stateless_when_store_is_false( item for item in follow_up_call["input"] if isinstance(item, dict) and item.get("type") == "reasoning" ] assert bool(reasoning_items) is (store is False) + + +@pytest.mark.asyncio +async def test_responses_discovery_logs_sanitized_caller_headers(monkeypatch: pytest.MonkeyPatch): + from litellm.proxy._experimental.mcp_server import operations + from litellm.proxy._experimental.mcp_server import mcp_server_manager + + headers: Final = { + "x-app-id": "app-a", "x-nuid": "user-a", "x-user-id": "identity-a", + "x-mcp-deepwiki-authorization": "upstream-sentinel", "authorization": "proxy-sentinel", + } + manager: Final = types.SimpleNamespace( + get_registry=MagicMock(return_value={}), + get_allowed_mcp_servers=AsyncMock(return_value=[]), + get_mcp_servers_from_ids=MagicMock(return_value=[]), + ) + logger: Final = MagicMock(model_call_details={}) + logger.async_success_handler = AsyncMock() + setup: Final = MagicMock(return_value=(logger, None)) + monkeypatch.setattr(mcp_server_manager, "global_mcp_server_manager", manager) + monkeypatch.setattr(operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[])) + monkeypatch.setattr(operations, "function_setup", setup) + response: Final = ResponsesAPIResponse( + id="resp_test", created_at=1234567891, model="test-model", object="response", + status="completed", output=[], parallel_tool_calls=False, tool_choice="auto", tools=[], + ) + monkeypatch.setattr(responses_main, "aresponses", AsyncMock(return_value=response)) + result: Final = await responses_main.aresponses_api_with_mcp( + input="hi", model="test-model", tools=[{"type": "mcp", "server_url": "litellm_proxy"}], + secret_fields={"raw_headers": headers}, + ) + assert result is response + logger.async_success_handler.assert_awaited_once() + logged: Final = setup.call_args.kwargs["metadata"]["headers"] + assert logged == {"x-app-id": "app-a", "x-nuid": "user-a", "x-user-id": "identity-a"} + assert headers["x-mcp-deepwiki-authorization"] == "upstream-sentinel" From ecce7cdd9c8eae08931b4a89b1af9ba13cf7201b Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:29:50 -0700 Subject: [PATCH 11/11] fix(proxy_cli): import proxy_server once on script-style boot (#42584) Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> --- litellm/proxy/proxy_cli.py | 41 ++++------------ tests/test_litellm/proxy/test_proxy_cli.py | 57 ++++++++++++++++------ 2 files changed, 52 insertions(+), 46 deletions(-) diff --git a/litellm/proxy/proxy_cli.py b/litellm/proxy/proxy_cli.py index 40140974198..ac69f2e3894 100644 --- a/litellm/proxy/proxy_cli.py +++ b/litellm/proxy/proxy_cli.py @@ -33,21 +33,20 @@ else: FastAPI = Any -def _deprioritize_script_dir_in_sys_path() -> None: +def _drop_script_dir_from_sys_path() -> None: """Stop ``litellm/proxy`` modules from shadowing installed packages. Running this file as a script puts its own directory at ``sys.path[0]``, so ``import a2a`` resolves to ``litellm/proxy/a2a`` instead of the ``a2a`` SDK - and A2A agent calls fail. The entry is moved to the end rather than dropped, - because the sibling-import fallbacks in this module (``from proxy_server - import ...``) still need it. No-op under the ``litellm`` console script. + and ``proxy_server`` resolves to a second copy of + ``litellm.proxy.proxy_server``. No-op under the ``litellm`` console script. """ script_dir: Final = os.path.dirname(os.path.abspath(__file__)) if sys.path and os.path.abspath(sys.path[0]) == script_dir: - sys.path.append(sys.path.pop(0)) + sys.path.pop(0) -_deprioritize_script_dir_in_sys_path() +_drop_script_dir_from_sys_path() sys.path.append(os.getcwd()) config_filename: Final = "litellm.secrets" @@ -881,7 +880,7 @@ class ProxyInitializationHelpers: default=False, help="Use prisma db push instead of prisma migrate for database schema updates", ) -@click.option("--local", is_flag=True, default=False, help="for local debugging") +@click.option("--local", is_flag=True, default=False, help="no-op, kept for backwards compatibility") @click.option( "--skip_server_startup", is_flag=True, @@ -1058,35 +1057,15 @@ def run_server( return args: Final = locals() - if local: - from proxy_server import ( + try: + from litellm.proxy.proxy_server import ( KeyManagementSettings, ProxyConfig, app, save_worker_config, ) - else: - try: - from .proxy_server import ( - KeyManagementSettings, - ProxyConfig, - app, - save_worker_config, - ) - except ModuleNotFoundError as e: - raise ModuleNotFoundError(f"Missing dependency {e}. Run `pip install 'litellm[proxy]'`") - except ImportError as e: - if "litellm[proxy]" in str(e): - # user is missing a proxy dependency, ask them to pip install litellm[proxy] - raise e - else: - # this is just a local/relative import error, user git cloned litellm - from proxy_server import ( - KeyManagementSettings, - ProxyConfig, - app, - save_worker_config, - ) + except ModuleNotFoundError as e: + raise ModuleNotFoundError(f"Missing dependency {e}. Run `pip install 'litellm[proxy]'`") from e if version is True: ProxyInitializationHelpers._echo_litellm_version() return diff --git a/tests/test_litellm/proxy/test_proxy_cli.py b/tests/test_litellm/proxy/test_proxy_cli.py index d2d71d6df05..b84efda3308 100644 --- a/tests/test_litellm/proxy/test_proxy_cli.py +++ b/tests/test_litellm/proxy/test_proxy_cli.py @@ -10,6 +10,8 @@ import pytest import builtins +import runpy +import sys import types import urllib.parse as urlparse @@ -18,6 +20,7 @@ import yaml from uvicorn.config import LOOP_FACTORIES from uvicorn.importer import import_from_string +from litellm.proxy import proxy_cli from litellm.proxy.proxy_cli import ProxyInitializationHelpers, run_server @@ -636,6 +639,36 @@ class TestProxyInitializationHelpers: ), f"exit_code={result.exit_code}, output={result.output}" mock_uvicorn_run.assert_called_once() + @patch("uvicorn.run") + @patch("atexit.register") + @patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database") + @patch("litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False) + def test_script_boot_imports_the_package_proxy_server( + self, mock_should_update, mock_setup_db, mock_atexit_register, mock_uvicorn_run + ): + package_proxy_server = MagicMock( + app=MagicMock(), + ProxyConfig=MagicMock(), + KeyManagementSettings=MagicMock(), + save_worker_config=MagicMock(), + ) + sibling_proxy_server = types.ModuleType("proxy_server") + clean_env = {k: v for k, v in os.environ.items() if k not in ("DATABASE_URL", "DIRECT_URL")} + with ( + patch.dict(os.environ, clean_env, clear=True), + patch.dict( + "sys.modules", + {"proxy_server": sibling_proxy_server, "litellm.proxy.proxy_server": package_proxy_server}, + ), + patch.object(sys, "argv", ["proxy_cli.py", "--skip_server_startup"]), + patch.object(sys, "path", list(sys.path)), + pytest.raises(SystemExit) as exit_info, + ): + runpy.run_path(proxy_cli.__file__, run_name="__main__") + + assert exit_info.value.code == 0 + package_proxy_server.save_worker_config.assert_called_once() + @patch("uvicorn.run") @patch("atexit.register") @patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database") @@ -1945,13 +1978,18 @@ class TestProxyInitializationHelpers: mock_proxy_config_instance.get_config = mock_get_config mock_proxy_config.return_value = mock_proxy_config_instance - mock_proxy_server_module = MagicMock(app=mock_app) + mock_proxy_server_module = MagicMock( + app=mock_app, + ProxyConfig=mock_proxy_config, + KeyManagementSettings=mock_key_mgmt, + save_worker_config=mock_save_worker_config, + ) # Only remove DATABASE_URL and DIRECT_URL to prevent the database setup # code path from running. Do NOT use clear=True as it removes PATH, HOME, # etc., which causes imports inside run_server to break in CI (the real - # litellm.proxy.proxy_server import at line 820 of proxy_cli.py has heavy - # side effects that fail without a proper environment). + # litellm.proxy.proxy_server import has heavy side effects that fail + # without a proper environment). env_overrides = { "DATABASE_URL": "", "DIRECT_URL": "", @@ -1967,18 +2005,7 @@ class TestProxyInitializationHelpers: with ( patch.dict( "sys.modules", - { - "proxy_server": MagicMock( - app=mock_app, - ProxyConfig=mock_proxy_config, - KeyManagementSettings=mock_key_mgmt, - save_worker_config=mock_save_worker_config, - ), - # Also mock litellm.proxy.proxy_server to prevent the real - # import at line 820 of proxy_cli.py which has heavy side - # effects (FastAPI app init, logging setup, etc.) - "litellm.proxy.proxy_server": mock_proxy_server_module, - }, + {"litellm.proxy.proxy_server": mock_proxy_server_module}, ), patch( "litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"