From 7a8226e75275ea87b82e501d6a89f6a8981d4d78 Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 2 Sep 2026 19:40:53 +0000 Subject: [PATCH 01/23] fix(model_prices): registry audit 2026-09-02, add claude-mythos-5-1 and gpt-daybreak aliases, fix gpt-5.5 Fast and W&B pricing Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 153 +++++++++++++++--- model_prices_and_context_window.json | 153 +++++++++++++++--- tests/test_litellm/test_cost_calculator.py | 5 + .../test_daybreak_model_metadata.py | 27 +++- 4 files changed, 301 insertions(+), 37 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2846d12db6e..7cf956edfdd 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -29620,7 +29620,45 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/daybreak-red-latest", + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "gpt-daybreak-red-latest": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": 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, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "supports_parallel_function_calling": true }, @@ -29660,7 +29698,45 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/daybreak-blue-latest", + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", + "supports_parallel_function_calling": true + }, + "gpt-daybreak-blue-latest": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_streaming": 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, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "supports_parallel_function_calling": true }, "chat-latest": { @@ -29699,12 +29775,12 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -29714,7 +29790,7 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { @@ -29756,12 +29832,12 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -29771,7 +29847,7 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { @@ -46311,8 +46387,8 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "wandb", "mode": "chat" }, @@ -46330,8 +46406,8 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "wandb", "mode": "chat" }, @@ -46396,8 +46472,8 @@ "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, - "input_cost_per_token": 0.135, - "output_cost_per_token": 0.54, + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, "litellm_provider": "wandb", "mode": "chat" }, @@ -46405,8 +46481,8 @@ "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, - "input_cost_per_token": 0.114, - "output_cost_per_token": 0.275, + "input_cost_per_token": 1.14e-06, + "output_cost_per_token": 2.75e-06, "litellm_provider": "wandb", "mode": "chat" }, @@ -46424,8 +46500,8 @@ "max_tokens": 64000, "max_input_tokens": 64000, "max_output_tokens": 64000, - "input_cost_per_token": 0.017, - "output_cost_per_token": 0.066, + "input_cost_per_token": 1.7e-07, + "output_cost_per_token": 6.6e-07, "litellm_provider": "wandb", "mode": "chat" }, @@ -54419,6 +54495,47 @@ "us": 1.1 } }, + "claude-mythos-5-1": { + "deprecation_date": "2027-09-01", + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 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_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview" + }, "claude-mythos-preview": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2846d12db6e..7cf956edfdd 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -29620,7 +29620,45 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/daybreak-red-latest", + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "gpt-daybreak-red-latest": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": 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, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "supports_parallel_function_calling": true }, @@ -29660,7 +29698,45 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/daybreak-blue-latest", + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", + "supports_parallel_function_calling": true + }, + "gpt-daybreak-blue-latest": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_streaming": 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, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "supports_parallel_function_calling": true }, "chat-latest": { @@ -29699,12 +29775,12 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -29714,7 +29790,7 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { @@ -29756,12 +29832,12 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -29771,7 +29847,7 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { @@ -46311,8 +46387,8 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "wandb", "mode": "chat" }, @@ -46330,8 +46406,8 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "wandb", "mode": "chat" }, @@ -46396,8 +46472,8 @@ "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, - "input_cost_per_token": 0.135, - "output_cost_per_token": 0.54, + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, "litellm_provider": "wandb", "mode": "chat" }, @@ -46405,8 +46481,8 @@ "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, - "input_cost_per_token": 0.114, - "output_cost_per_token": 0.275, + "input_cost_per_token": 1.14e-06, + "output_cost_per_token": 2.75e-06, "litellm_provider": "wandb", "mode": "chat" }, @@ -46424,8 +46500,8 @@ "max_tokens": 64000, "max_input_tokens": 64000, "max_output_tokens": 64000, - "input_cost_per_token": 0.017, - "output_cost_per_token": 0.066, + "input_cost_per_token": 1.7e-07, + "output_cost_per_token": 6.6e-07, "litellm_provider": "wandb", "mode": "chat" }, @@ -54419,6 +54495,47 @@ "us": 1.1 } }, + "claude-mythos-5-1": { + "deprecation_date": "2027-09-01", + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 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_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview" + }, "claude-mythos-preview": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index 7c2174018e8..862d77f01b2 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -175,6 +175,11 @@ def test_wandb_model_api_pricing_entries(_local_model_cost_map): expected_pricing = { "wandb/moonshotai/Kimi-K2.5": (6e-07, 3e-06), "wandb/MiniMaxAI/MiniMax-M2.5": (3e-07, 1.2e-06), + "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": (1e-07, 1e-07), + "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": (1e-07, 1e-07), + "wandb/deepseek-ai/DeepSeek-R1-0528": (1.35e-06, 5.4e-06), + "wandb/deepseek-ai/DeepSeek-V3-0324": (1.14e-06, 2.75e-06), + "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": (1.7e-07, 6.6e-07), } for model_name, (input_cost, output_cost) in expected_pricing.items(): diff --git a/tests/test_litellm/test_daybreak_model_metadata.py b/tests/test_litellm/test_daybreak_model_metadata.py index d04cca3c077..068bc01e103 100644 --- a/tests/test_litellm/test_daybreak_model_metadata.py +++ b/tests/test_litellm/test_daybreak_model_metadata.py @@ -14,6 +14,17 @@ DAYBREAK_MODELS = ( ) BLUE_ALIAS = "daybreak-blue-latest" BLUE_SNAPSHOT = "gpt-5.6-sol" +OFFICIAL_ALIAS_SNAPSHOTS = ( + ("gpt-daybreak-blue-latest", "gpt-5.6-sol"), + ("gpt-daybreak-red-latest", "gpt-5.6-cyber"), +) +PRICE_FIELDS = ( + "input_cost_per_token", + "output_cost_per_token", + "cache_read_input_token_cost", + "input_cost_per_token_above_272k_tokens", + "output_cost_per_token_above_272k_tokens", +) def _load(path): @@ -44,7 +55,21 @@ def test_blue_alias_matches_its_snapshot_computer_use(): assert cost_map[BLUE_SNAPSHOT]["supports_computer_use"] is True -@pytest.mark.parametrize("model", (*DAYBREAK_MODELS, BLUE_SNAPSHOT)) +@pytest.mark.parametrize(("alias", "snapshot"), OFFICIAL_ALIAS_SNAPSHOTS) +def test_official_alias_tracks_snapshot(alias, snapshot): + cost_map = _load(MAIN_PATH) + alias_info = cost_map[alias] + snapshot_info = cost_map[snapshot] + + assert alias_info["supported_endpoints"] == ["/v1/responses"] + assert alias_info["source"] == f"https://developers.openai.com/api/docs/models/{alias}" + assert {field: alias_info.get(field) for field in PRICE_FIELDS} == { + field: snapshot_info.get(field) for field in PRICE_FIELDS + } + assert alias_info["max_output_tokens"] == snapshot_info["max_output_tokens"] + + +@pytest.mark.parametrize("model", (*DAYBREAK_MODELS, BLUE_SNAPSHOT, *(alias for alias, _ in OFFICIAL_ALIAS_SNAPSHOTS))) def test_backup_matches_main(model): main_cost = _load(MAIN_PATH) backup_cost = _load(BACKUP_PATH) From 9c5b20abdd7978c3b6d52b9dff1f8703049ff4dc Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 2 Sep 2026 20:07:21 +0000 Subject: [PATCH 02/23] fix(model_prices): add Nebius, watsonx and Volcengine models and correct watsonx list prices Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 475 ++++++++++++++++-- model_prices_and_context_window.json | 475 ++++++++++++++++-- 2 files changed, 856 insertions(+), 94 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7cf956edfdd..a6967c12c94 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -35226,16 +35226,16 @@ "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2e-07, + "max_tokens": 110000, + "max_input_tokens": 110000, + "max_output_tokens": 110000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 128000, @@ -35347,15 +35347,15 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { "max_tokens": 32768, @@ -35436,16 +35436,16 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices" + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { "max_tokens": 131072, @@ -35470,6 +35470,320 @@ "supports_vision": true, "source": "https://nebius.com/prices" }, + "nebius/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" + }, + "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" + }, + "nebius/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 3.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" + }, + "nebius/MiniMaxAI/MiniMax-M2.5": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" + }, + "nebius/MiniMaxAI/MiniMax-M3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" + }, + "nebius/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" + }, + "nebius/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" + }, + "nebius/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" + }, + "nebius/NousResearch/Hermes-4-405B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" + }, + "nebius/NousResearch/Hermes-4-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" + }, + "nebius/nvidia/Cosmos3-Super-Reasoner": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" + }, + "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" + }, + "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" + }, + "nebius/nvidia/Nemotron-3-Nano-Omni": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" + }, + "nebius/nvidia/nemotron-3-super-120b-a12b": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" + }, + "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" + }, + "nebius/nvidia/Nemotron-3_5-Lightning": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" + }, + "nebius/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" + }, + "nebius/openbmb/MiniCPM-V-4_5": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 6.58e-07, + "output_cost_per_token": 1.11e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" + }, + "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" + }, + "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" + }, + "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" + }, + "nebius/Qwen/Qwen3.5-397B-A17B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" + }, + "nebius/zai-org/GLM-5.1": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" + }, + "nebius/zai-org/GLM-5.2": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" + }, + "nebius/zai-org/GLM-5.3-Flash": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash" + }, "nebius/BAAI/bge-en-icl": { "max_tokens": 32768, "max_input_tokens": 32768, @@ -35497,6 +35811,15 @@ "mode": "embedding", "source": "https://nebius.com/prices" }, + "nebius/Qwen/Qwen3-Embedding-8B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" + }, "nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", @@ -46551,16 +46874,30 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.908e-06, + "output_cost_per_token": 1.908e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" + }, + "watsonx/bigscience/mt0-xxl": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.908e-06, + "output_cost_per_token": 1.908e-06, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { "max_tokens": 8192, @@ -46623,16 +46960,17 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 20480, - "max_input_tokens": 20480, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 20480, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.5e-07, + "input_cost_per_token": 6.36e-08, + "output_cost_per_token": 2.65e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { "max_tokens": 8192, @@ -46755,28 +47093,43 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 128000, - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 7.1e-07, + "input_cost_per_token": 7.526e-07, + "output_cost_per_token": 7.526e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.4e-06, + "input_cost_per_token": 3.71e-07, + "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" + }, + "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 128000, + "input_cost_per_token": 3.71e-07, + "output_cost_per_token": 1.484e-06, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { "max_tokens": 128000, @@ -46815,16 +47168,17 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 32000, - "max_input_tokens": 32000, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 1.06e-07, + "output_cost_per_token": 3.18e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { "max_tokens": 128000, @@ -46839,16 +47193,17 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 8192, - "max_input_tokens": 8192, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 1.59e-07, + "output_cost_per_token": 6.36e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { "max_tokens": 8192, @@ -53520,6 +53875,32 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "source": "https://www.volcengine.com/docs/82379/1330310", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "source": "https://www.volcengine.com/docs/82379/1330310", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7cf956edfdd..a6967c12c94 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -35226,16 +35226,16 @@ "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2e-07, + "max_tokens": 110000, + "max_input_tokens": 110000, + "max_output_tokens": 110000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 128000, @@ -35347,15 +35347,15 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { "max_tokens": 32768, @@ -35436,16 +35436,16 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices" + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { "max_tokens": 131072, @@ -35470,6 +35470,320 @@ "supports_vision": true, "source": "https://nebius.com/prices" }, + "nebius/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" + }, + "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" + }, + "nebius/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 3.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" + }, + "nebius/MiniMaxAI/MiniMax-M2.5": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" + }, + "nebius/MiniMaxAI/MiniMax-M3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" + }, + "nebius/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" + }, + "nebius/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" + }, + "nebius/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" + }, + "nebius/NousResearch/Hermes-4-405B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" + }, + "nebius/NousResearch/Hermes-4-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" + }, + "nebius/nvidia/Cosmos3-Super-Reasoner": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" + }, + "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" + }, + "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" + }, + "nebius/nvidia/Nemotron-3-Nano-Omni": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" + }, + "nebius/nvidia/nemotron-3-super-120b-a12b": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" + }, + "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" + }, + "nebius/nvidia/Nemotron-3_5-Lightning": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" + }, + "nebius/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" + }, + "nebius/openbmb/MiniCPM-V-4_5": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 6.58e-07, + "output_cost_per_token": 1.11e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" + }, + "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" + }, + "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" + }, + "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" + }, + "nebius/Qwen/Qwen3.5-397B-A17B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" + }, + "nebius/zai-org/GLM-5.1": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" + }, + "nebius/zai-org/GLM-5.2": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" + }, + "nebius/zai-org/GLM-5.3-Flash": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash" + }, "nebius/BAAI/bge-en-icl": { "max_tokens": 32768, "max_input_tokens": 32768, @@ -35497,6 +35811,15 @@ "mode": "embedding", "source": "https://nebius.com/prices" }, + "nebius/Qwen/Qwen3-Embedding-8B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" + }, "nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", @@ -46551,16 +46874,30 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.908e-06, + "output_cost_per_token": 1.908e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" + }, + "watsonx/bigscience/mt0-xxl": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.908e-06, + "output_cost_per_token": 1.908e-06, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { "max_tokens": 8192, @@ -46623,16 +46960,17 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 20480, - "max_input_tokens": 20480, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 20480, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.5e-07, + "input_cost_per_token": 6.36e-08, + "output_cost_per_token": 2.65e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { "max_tokens": 8192, @@ -46755,28 +47093,43 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 128000, - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 7.1e-07, + "input_cost_per_token": 7.526e-07, + "output_cost_per_token": 7.526e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.4e-06, + "input_cost_per_token": 3.71e-07, + "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" + }, + "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 128000, + "input_cost_per_token": 3.71e-07, + "output_cost_per_token": 1.484e-06, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { "max_tokens": 128000, @@ -46815,16 +47168,17 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 32000, - "max_input_tokens": 32000, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 1.06e-07, + "output_cost_per_token": 3.18e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { "max_tokens": 128000, @@ -46839,16 +47193,17 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 8192, - "max_input_tokens": 8192, + "max_tokens": 131072, + "max_input_tokens": 131072, "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 1.59e-07, + "output_cost_per_token": 6.36e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { "max_tokens": 8192, @@ -53520,6 +53875,32 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "source": "https://www.volcengine.com/docs/82379/1330310", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "source": "https://www.volcengine.com/docs/82379/1330310", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, From 60ffde65e0a1929c372023333af302a7793c119b Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 2 Sep 2026 20:08:43 +0000 Subject: [PATCH 03/23] fix(model_prices): drop unpriced Volcengine Seed 2.1 entries, they would record zero spend Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 26 ------------------- model_prices_and_context_window.json | 26 ------------------- 2 files changed, 52 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a6967c12c94..f6316fba884 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -53875,32 +53875,6 @@ } ] }, - "volcengine/doubao-seed-2-1-pro-260628": { - "litellm_provider": "volcengine", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "volcengine/doubao-seed-2-1-turbo-260628": { - "litellm_provider": "volcengine", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true - }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a6967c12c94..f6316fba884 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -53875,32 +53875,6 @@ } ] }, - "volcengine/doubao-seed-2-1-pro-260628": { - "litellm_provider": "volcengine", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "volcengine/doubao-seed-2-1-turbo-260628": { - "litellm_provider": "volcengine", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true - }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, From 211f5d2d102a5f18f43e529c4f8510974e06f9b4 Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 2 Sep 2026 20:19:31 +0000 Subject: [PATCH 04/23] test(savings): update gpt-5.5 priority baseline to the published 2.5x fast-mode rate Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- tests/test_litellm/proxy/spend_tracking/test_savings.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/test_litellm/proxy/spend_tracking/test_savings.py b/tests/test_litellm/proxy/spend_tracking/test_savings.py index 7dd18587df3..3f775d82b7f 100644 --- a/tests/test_litellm/proxy/spend_tracking/test_savings.py +++ b/tests/test_litellm/proxy/spend_tracking/test_savings.py @@ -852,7 +852,7 @@ def test_the_served_arm_is_read_from_the_record_not_repriced(): @pytest.mark.parametrize( "basis, expected_multiplier", [ - pytest.param({"service_tier": "priority"}, 2.0, id="priority tier doubles the baseline"), + pytest.param({"service_tier": "priority"}, 2.5, id="priority tier uplifts the baseline"), pytest.param({"data_residency": "eu"}, 1.1, id="eu residency uplifts the baseline"), pytest.param({}, 1.0, id="no basis recorded prices at standard"), pytest.param(None, 1.0, id="row predating the field prices at standard"), @@ -872,7 +872,8 @@ def test_the_baseline_is_priced_on_the_basis_the_request_was_billed_at(basis, ex """ gpt = litellm.get_model_info("gpt-5.5", "openai") haiku = litellm.get_model_info("claude-haiku-4-5", "anthropic") - assert gpt.get("input_cost_per_token_priority") == 2 * gpt["input_cost_per_token"] + assert gpt.get("input_cost_per_token_priority") == pytest.approx(2.5 * gpt["input_cost_per_token"]) + assert gpt.get("output_cost_per_token_priority") == pytest.approx(2.5 * gpt["output_cost_per_token"]) assert gpt.get("regional_processing_uplift_multiplier_eu") == 1.1 assert haiku.get("input_cost_per_token_priority") is None, "served model must not move with the basis" assert haiku.get("regional_processing_uplift_multiplier_eu") is None From 671559e591ccbc24d540e9bf9be76f8631f59f16 Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 2 Sep 2026 20:35:29 +0000 Subject: [PATCH 05/23] fix(model_prices): set watsonx max_tokens equal to max_output_tokens per registry convention Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 12 ++++++------ model_prices_and_context_window.json | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f6316fba884..2e717b52b28 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -46960,7 +46960,7 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 131072, + "max_tokens": 20480, "max_input_tokens": 131072, "max_output_tokens": 20480, "input_cost_per_token": 6.36e-08, @@ -47093,7 +47093,7 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 131072, + "max_tokens": 128000, "max_input_tokens": 131072, "max_output_tokens": 128000, "input_cost_per_token": 7.526e-07, @@ -47106,7 +47106,7 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 131072, + "max_tokens": 128000, "max_input_tokens": 131072, "max_output_tokens": 128000, "input_cost_per_token": 3.71e-07, @@ -47119,7 +47119,7 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 131072, + "max_tokens": 128000, "max_input_tokens": 131072, "max_output_tokens": 128000, "input_cost_per_token": 3.71e-07, @@ -47168,7 +47168,7 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 131072, + "max_tokens": 32000, "max_input_tokens": 131072, "max_output_tokens": 32000, "input_cost_per_token": 1.06e-07, @@ -47193,7 +47193,7 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 131072, + "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 1.59e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f6316fba884..2e717b52b28 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -46960,7 +46960,7 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 131072, + "max_tokens": 20480, "max_input_tokens": 131072, "max_output_tokens": 20480, "input_cost_per_token": 6.36e-08, @@ -47093,7 +47093,7 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 131072, + "max_tokens": 128000, "max_input_tokens": 131072, "max_output_tokens": 128000, "input_cost_per_token": 7.526e-07, @@ -47106,7 +47106,7 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 131072, + "max_tokens": 128000, "max_input_tokens": 131072, "max_output_tokens": 128000, "input_cost_per_token": 3.71e-07, @@ -47119,7 +47119,7 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 131072, + "max_tokens": 128000, "max_input_tokens": 131072, "max_output_tokens": 128000, "input_cost_per_token": 3.71e-07, @@ -47168,7 +47168,7 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 131072, + "max_tokens": 32000, "max_input_tokens": 131072, "max_output_tokens": 32000, "input_cost_per_token": 1.06e-07, @@ -47193,7 +47193,7 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 131072, + "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 1.59e-07, From e148868f0c773ef933bba9d84cc3e2d34c572554 Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 2 Sep 2026 20:38:45 +0000 Subject: [PATCH 06/23] fix(model_prices): set watsonx max_output_tokens from IBM's documented maximum new tokens Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 24 +++++++++---------- model_prices_and_context_window.json | 24 +++++++++---------- 2 files changed, 24 insertions(+), 24 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2e717b52b28..1935bc97c3b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -46960,9 +46960,9 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 20480, + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 20480, + "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, "output_cost_per_token": 2.65e-07, "litellm_provider": "watsonx", @@ -47093,9 +47093,9 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 128000, + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 128000, + "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, "output_cost_per_token": 7.526e-07, "litellm_provider": "watsonx", @@ -47106,9 +47106,9 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 128000, + "max_tokens": 8192, "max_input_tokens": 131072, - "max_output_tokens": 128000, + "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", @@ -47119,9 +47119,9 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 128000, + "max_tokens": 8192, "max_input_tokens": 131072, - "max_output_tokens": 128000, + "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", @@ -47168,9 +47168,9 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 32000, + "max_tokens": 16384, "max_input_tokens": 131072, - "max_output_tokens": 32000, + "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, "output_cost_per_token": 3.18e-07, "litellm_provider": "watsonx", @@ -47193,9 +47193,9 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 8192, + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 8192, + "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, "output_cost_per_token": 6.36e-07, "litellm_provider": "watsonx", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2e717b52b28..1935bc97c3b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -46960,9 +46960,9 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 20480, + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 20480, + "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, "output_cost_per_token": 2.65e-07, "litellm_provider": "watsonx", @@ -47093,9 +47093,9 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 128000, + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 128000, + "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, "output_cost_per_token": 7.526e-07, "litellm_provider": "watsonx", @@ -47106,9 +47106,9 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 128000, + "max_tokens": 8192, "max_input_tokens": 131072, - "max_output_tokens": 128000, + "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", @@ -47119,9 +47119,9 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 128000, + "max_tokens": 8192, "max_input_tokens": 131072, - "max_output_tokens": 128000, + "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", @@ -47168,9 +47168,9 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 32000, + "max_tokens": 16384, "max_input_tokens": 131072, - "max_output_tokens": 32000, + "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, "output_cost_per_token": 3.18e-07, "litellm_provider": "watsonx", @@ -47193,9 +47193,9 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 8192, + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 8192, + "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, "output_cost_per_token": 6.36e-07, "litellm_provider": "watsonx", From 55a5f142e612d99931500091e4a4d7fa13676060 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 13:23:02 +0000 Subject: [PATCH 07/23] fix(model_prices): add azure_ai Codestral-2501 and FW-Nemotron-Lightning-3.5, sync Azure and Vertex deprecation dates, fix novita gpt-oss vision flags Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 55 +++++++++++++++++-- model_prices_and_context_window.json | 55 +++++++++++++++++-- .../azure_ai/test_azure_ai_cost_calculator.py | 13 +++++ .../test_azure_ai_fw_models_metadata.py | 25 +++++++++ 4 files changed, 136 insertions(+), 12 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a3030d2e33d..4e1869a83a8 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3264,7 +3264,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-12-05" }, "azure_ai/claude-opus-5": { "deprecation_date": "2027-07-08", @@ -8813,7 +8814,7 @@ "supports_web_search": false }, "azure/us/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2026-10-14", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 6e-08, @@ -9333,6 +9334,26 @@ "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true }, + "azure_ai/Codestral-2501": { + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true + }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", "mode": "image_generation", @@ -9611,6 +9632,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { "cache_read_input_token_cost": 1.19e-07, "input_cost_per_token": 6e-07, @@ -44923,7 +44964,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-03-01" }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", @@ -44994,7 +45036,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-03-01" }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", @@ -51227,7 +51270,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true @@ -51343,7 +51386,7 @@ "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a3030d2e33d..4e1869a83a8 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3264,7 +3264,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-12-05" }, "azure_ai/claude-opus-5": { "deprecation_date": "2027-07-08", @@ -8813,7 +8814,7 @@ "supports_web_search": false }, "azure/us/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2026-10-14", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 6e-08, @@ -9333,6 +9334,26 @@ "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true }, + "azure_ai/Codestral-2501": { + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true + }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", "mode": "image_generation", @@ -9611,6 +9632,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { "cache_read_input_token_cost": 1.19e-07, "input_cost_per_token": 6e-07, @@ -44923,7 +44964,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-03-01" }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", @@ -44994,7 +45036,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-03-01" }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", @@ -51227,7 +51270,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true @@ -51343,7 +51386,7 @@ "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true diff --git a/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py b/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py index 20260c744f8..fd6fab6a521 100644 --- a/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py +++ b/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py @@ -499,3 +499,16 @@ class TestAzureAIServiceTierCostCalculation: assert flex_prompt < standard_prompt assert flex_completion < standard_completion + + +def test_codestral_2501_model_info_and_cost(): + model_info = get_model_info(model="Codestral-2501", custom_llm_provider="azure_ai") + usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000) + + prompt_cost, completion_cost = cost_per_token(model="Codestral-2501", usage=usage) + + assert model_info["mode"] == "chat" + assert model_info["max_input_tokens"] == 256000 + assert model_info["max_output_tokens"] == 4096 + assert prompt_cost == pytest.approx(0.3) + assert completion_cost == pytest.approx(0.9) diff --git a/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py b/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py index 9917ab41b42..f3618572622 100644 --- a/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py +++ b/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py @@ -176,6 +176,7 @@ def test_azure_ai_fw_model_info(use_local_model_cost_map, model_key, expected): ("FW-MiniMax-M2.5", 0.33, 1.32), ("FW-Inkling", 1.0, 4.05), ("FW-Nemotron-3-Ultra-NVFP4", 0.6, 2.4), + ("FW-Nemotron-Lightning-3.5-30B-A3B", 0.06, 0.22), ], ) def test_azure_ai_fw_cost_per_token( @@ -196,6 +197,30 @@ def test_azure_ai_fw_cost_per_token( assert completion_cost == pytest.approx(expected_completion) +def test_azure_ai_fw_nemotron_lightning_model_info(use_local_model_cost_map): + model_info = use_local_model_cost_map.get_model_info(model="azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B") + + assert model_info["litellm_provider"] == "azure_ai" + assert model_info["mode"] == "chat" + assert model_info["input_cost_per_token"] == pytest.approx(6e-08) + assert model_info["output_cost_per_token"] == pytest.approx(2.2e-07) + assert model_info["cache_read_input_token_cost"] == pytest.approx(1e-08) + assert model_info["max_input_tokens"] == 262144 + assert model_info["supports_function_calling"] is True + assert model_info["supports_reasoning"] is True + assert model_info["supports_tool_choice"] is True + assert model_info["supports_prompt_caching"] is True + assert model_info["supports_vision"] is False + + +def test_azure_ai_fw_nemotron_lightning_supports_tool_choice(use_local_model_cost_map): + from litellm.llms.azure_ai.chat.transformation import AzureAIStudioConfig + + supported_params = AzureAIStudioConfig().get_supported_openai_params("FW-Nemotron-Lightning-3.5-30B-A3B") + + assert "tool_choice" in supported_params + + def test_azure_ai_fw_kimi_k26_case_insensitive_lookup(use_local_model_cost_map): upper = use_local_model_cost_map.get_model_info(model="azure_ai/FW-Kimi-K2.6") lower = use_local_model_cost_map.get_model_info(model="azure_ai/fw-kimi-k2.6") From f26407aa8ceb54e623ab6629a4a6524ad1dd8907 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 13:43:48 +0000 Subject: [PATCH 08/23] feat(registry): add azure_ai/MAI-Thinking-1 from Azure Retail Prices and Foundry docs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 24 +++++++++++++++++++ model_prices_and_context_window.json | 24 +++++++++++++++++++ .../azure_ai/test_azure_ai_cost_calculator.py | 18 +++++++++++++- 3 files changed, 65 insertions(+), 1 deletion(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4e1869a83a8..23ce80f9968 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -9713,6 +9713,30 @@ "/v1/images/generations" ] }, + "azure_ai/MAI-Thinking-1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "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, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 4e1869a83a8..23ce80f9968 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -9713,6 +9713,30 @@ "/v1/images/generations" ] }, + "azure_ai/MAI-Thinking-1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "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, diff --git a/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py b/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py index fd6fab6a521..9612d97d946 100644 --- a/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py +++ b/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py @@ -501,7 +501,7 @@ class TestAzureAIServiceTierCostCalculation: assert flex_completion < standard_completion -def test_codestral_2501_model_info_and_cost(): +def test_codestral_2501_model_info_and_cost(local_model_cost_map): model_info = get_model_info(model="Codestral-2501", custom_llm_provider="azure_ai") usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000) @@ -512,3 +512,19 @@ def test_codestral_2501_model_info_and_cost(): assert model_info["max_output_tokens"] == 4096 assert prompt_cost == pytest.approx(0.3) assert completion_cost == pytest.approx(0.9) + + +def test_mai_thinking_1_model_info_and_cost(local_model_cost_map): + model_info = get_model_info(model="MAI-Thinking-1", custom_llm_provider="azure_ai") + usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000) + + prompt_cost, completion_cost = cost_per_token(model="MAI-Thinking-1", usage=usage) + + assert model_info["mode"] == "chat" + assert model_info["max_input_tokens"] == 256000 + assert model_info["max_output_tokens"] == 64000 + assert model_info["cache_read_input_token_cost"] == pytest.approx(2e-07) + assert model_info["supports_reasoning"] is True + assert model_info["supports_function_calling"] is True + assert prompt_cost == pytest.approx(2.0) + assert completion_cost == pytest.approx(8.0) From 840173e7789cbd8d9aa8cc836d8827427daf0201 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 13:48:25 +0000 Subject: [PATCH 09/23] feat(registry): add azure_ai/mistral-ocr-4-0 page and annotation prices from Azure Retail Prices Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../model_prices_and_context_window_backup.json | 10 ++++++++++ model_prices_and_context_window.json | 10 ++++++++++ .../llms/mistral/ocr/test_mistral_ocr_cost.py | 14 ++++++++++++++ 3 files changed, 34 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 23ce80f9968..df25f312b04 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -10037,6 +10037,16 @@ ], "source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512" }, + "azure_ai/mistral-ocr-4-0": { + "litellm_provider": "azure_ai", + "ocr_cost_per_page": 0.004, + "annotation_cost_per_page": 0.005, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/" + }, "azure_ai/doc-intelligence/prebuilt-read": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.0015, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 23ce80f9968..df25f312b04 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -10037,6 +10037,16 @@ ], "source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512" }, + "azure_ai/mistral-ocr-4-0": { + "litellm_provider": "azure_ai", + "ocr_cost_per_page": 0.004, + "annotation_cost_per_page": 0.005, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/" + }, "azure_ai/doc-intelligence/prebuilt-read": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.0015, diff --git a/tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py b/tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py index a0e1616d4b2..40e54f71eeb 100644 --- a/tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py +++ b/tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py @@ -15,6 +15,7 @@ from litellm.cost_calculator import completion_cost from litellm.llms.base_llm.ocr.transformation import OCRPage, OCRResponse, OCRUsageInfo OCR4_COST_PER_PAGE = 0.004 +OCR4_ANNOTATION_COST_PER_PAGE = 0.005 REPO_ROOT = Path(__file__).parents[5] MAIN_COST_MAP = REPO_ROOT / "model_prices_and_context_window.json" @@ -133,3 +134,16 @@ def test_azure_doc_ai_annotation_pages_fall_back_to_ocr_rate(local_model_cost_ma call_type="ocr", ) assert cost == pytest.approx(AZURE_DOC_AI_COST_PER_PAGE) + + +def test_azure_ocr4_bills_ocr_and_annotation_pages_at_their_own_rates(local_model_cost_map) -> None: + info = litellm.get_model_info(model="azure_ai/mistral-ocr-4-0", custom_llm_provider="azure_ai") + assert info["ocr_cost_per_page"] == OCR4_COST_PER_PAGE + assert info["annotation_cost_per_page"] == OCR4_ANNOTATION_COST_PER_PAGE + cost = completion_cost( + completion_response=_annotated_ocr_response("mistral-ocr-4-0", 2, 3), + model="azure_ai/mistral-ocr-4-0", + custom_llm_provider="azure_ai", + call_type="ocr", + ) + assert cost == pytest.approx(2 * OCR4_COST_PER_PAGE + 3 * OCR4_ANNOTATION_COST_PER_PAGE) From 32a3a653124cd0b71982248732bd284e4272ebd0 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 19:35:30 +0000 Subject: [PATCH 10/23] fix(model_prices): add Lyria 3.5, Perplexity Agent API and OpenRouter first-party models, fix Nebius, Mistral, OpenRouter metadata Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 1051 ++++++++++++++++- model_prices_and_context_window.json | 1051 ++++++++++++++++- 2 files changed, 2002 insertions(+), 100 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 50e38072e80..724929a48f5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -26299,7 +26299,8 @@ "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, - "supports_web_search": false + "supports_web_search": false, + "output_cost_per_image": 0.08 }, "gemini/veo-2.0-generate-001": { "deprecation_date": "2026-06-30", @@ -33887,7 +33888,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, "mistral/ministral-14b-latest": { "input_cost_per_token": 2e-07, @@ -33902,7 +33904,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, "mistral/ministral-3b-2512": { "input_cost_per_token": 1e-07, @@ -33917,7 +33920,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, "mistral/ministral-3b-latest": { "input_cost_per_token": 1e-07, @@ -33932,7 +33936,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, "mistral/mistral-embed-2312": { "input_cost_per_token": 1e-07, @@ -35395,9 +35400,9 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", @@ -35715,9 +35720,9 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" }, "nebius/moonshotai/Kimi-K3": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "nebius", @@ -37585,8 +37590,8 @@ "input_cost_per_token": 5e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -37597,7 +37602,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/anthropic/claude-opus-4.5" }, "openrouter/anthropic/claude-opus-4.6": { "supports_adaptive_thinking": true, @@ -37632,8 +37638,8 @@ "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -37643,7 +37649,8 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/anthropic/claude-sonnet-4.5" }, "openrouter/anthropic/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, @@ -37651,8 +37658,8 @@ "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -37662,7 +37669,8 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/anthropic/claude-haiku-4.5" }, "openrouter/anthropic/claude-opus-4.7": { "supports_adaptive_thinking": true, @@ -37875,8 +37883,8 @@ "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_audio_output": true, @@ -37885,15 +37893,18 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_image_size": false + "supports_image_size": false, + "cache_read_input_token_cost": 3e-08, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/google/gemini-2.5-flash" }, "openrouter/google/gemini-2.5-pro": { "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_output": true, @@ -37901,7 +37912,10 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/google/gemini-2.5-pro" }, "openrouter/google/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -38292,14 +38306,15 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1.5e-06, "supports_tool_choice": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "source": "https://openrouter.ai/openai/gpt-3.5-turbo" }, "openrouter/openai/gpt-3.5-turbo-16k": { "input_cost_per_token": 3e-06, @@ -38376,14 +38391,17 @@ "input_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-06, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/openai/gpt-4o" }, "openrouter/openai/gpt-4o-2024-05-13": { "input_cost_per_token": 5e-06, @@ -38631,30 +38649,36 @@ "openrouter/openai/o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/openai/o3-mini" }, "openrouter/openai/o3-mini-high": { "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/openai/o3-mini-high" }, "openrouter/qwen/qwen-2.5-coder-32b-instruct": { "input_cost_per_token": 1.8e-07, @@ -39672,21 +39696,33 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": true, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.4e-05, + "cache_read_input_token_cost": 1.75e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.1": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 2.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-6": { "supports_adaptive_thinking": true, @@ -39696,7 +39732,11 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-7": { "supports_adaptive_thinking": true, @@ -39705,7 +39745,11 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", @@ -39713,21 +39757,33 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-haiku-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3-pro-preview": { "litellm_provider": "perplexity", @@ -39741,7 +39797,11 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-2.5-pro": { "litellm_provider": "perplexity", @@ -39770,7 +39830,11 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 6.25e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 2.8e-08, @@ -59010,5 +59074,892 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ] + }, + "gemini/lyria-3.5-clip-preview": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_image": 0.04, + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false + }, + "gemini/lyria-3.5-pro-preview": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "output_cost_per_image": 0.08 + }, + "perplexity/anthropic/claude-fable-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-4-8": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-sonnet-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-sonnet-4-6": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-terra": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_above_272k_tokens": 4e-07, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_above_272k_tokens": 5e-06, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4-mini": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 4.5e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4-nano": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.1-pro-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.1-flash-lite": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 2.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.5-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "cache_read_input_token_cost": 1.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.5-flash-lite": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 3e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.6-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.7-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.6": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.3": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-non-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-multi-agent": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/glm-5.3": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/glm-5.3-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 3e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/nemotron-3.5-lightning-30b-a3b": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.15e-08, + "output_cost_per_token": 1.7e-07, + "cache_read_input_token_cost": 1.15e-09, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "openrouter/anthropic/claude-fable-5": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-fable-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1e-06, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 1.25e-05 + }, + "openrouter/anthropic/claude-fable-5.1": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-fable-5.1", + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 1.25e-05 + }, + "openrouter/anthropic/claude-opus-4.8": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-opus-4.8", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 6.25e-06 + }, + "openrouter/anthropic/claude-sonnet-5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-sonnet-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 2.5e-06 + }, + "openrouter/google/gemini-2.5-flash-lite": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-flash-lite", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.5-flash": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.5-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.5-flash-lite": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.5-flash-lite", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 3e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.6-flash": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.6-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.7-flash": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.7-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.8-flash": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.8-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.1": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1.25e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.3-codex": { + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.4e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.3-codex", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1.75e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.4": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.4-mini": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 4.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.4-nano": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4-nano", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.5": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.6-luna": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.6-luna", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.6-terra": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.6-terra", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/o3": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/o4-mini": { + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o4-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.75e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.20": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.20", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.20-multi-agent": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.20-multi-agent", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.3": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 900000, + "max_tokens": 900000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 3e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.6": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.6", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-build-0.1": { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 230400, + "max_tokens": 230400, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-build-0.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 50e38072e80..724929a48f5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26299,7 +26299,8 @@ "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, - "supports_web_search": false + "supports_web_search": false, + "output_cost_per_image": 0.08 }, "gemini/veo-2.0-generate-001": { "deprecation_date": "2026-06-30", @@ -33887,7 +33888,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, "mistral/ministral-14b-latest": { "input_cost_per_token": 2e-07, @@ -33902,7 +33904,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, "mistral/ministral-3b-2512": { "input_cost_per_token": 1e-07, @@ -33917,7 +33920,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, "mistral/ministral-3b-latest": { "input_cost_per_token": 1e-07, @@ -33932,7 +33936,8 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, "mistral/mistral-embed-2312": { "input_cost_per_token": 1e-07, @@ -35395,9 +35400,9 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", @@ -35715,9 +35720,9 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" }, "nebius/moonshotai/Kimi-K3": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "nebius", @@ -37585,8 +37590,8 @@ "input_cost_per_token": 5e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -37597,7 +37602,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/anthropic/claude-opus-4.5" }, "openrouter/anthropic/claude-opus-4.6": { "supports_adaptive_thinking": true, @@ -37632,8 +37638,8 @@ "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -37643,7 +37649,8 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/anthropic/claude-sonnet-4.5" }, "openrouter/anthropic/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, @@ -37651,8 +37658,8 @@ "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -37662,7 +37669,8 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/anthropic/claude-haiku-4.5" }, "openrouter/anthropic/claude-opus-4.7": { "supports_adaptive_thinking": true, @@ -37875,8 +37883,8 @@ "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_audio_output": true, @@ -37885,15 +37893,18 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_image_size": false + "supports_image_size": false, + "cache_read_input_token_cost": 3e-08, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/google/gemini-2.5-flash" }, "openrouter/google/gemini-2.5-pro": { "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_output": true, @@ -37901,7 +37912,10 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/google/gemini-2.5-pro" }, "openrouter/google/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -38292,14 +38306,15 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1.5e-06, "supports_tool_choice": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "source": "https://openrouter.ai/openai/gpt-3.5-turbo" }, "openrouter/openai/gpt-3.5-turbo-16k": { "input_cost_per_token": 3e-06, @@ -38376,14 +38391,17 @@ "input_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-06, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/openai/gpt-4o" }, "openrouter/openai/gpt-4o-2024-05-13": { "input_cost_per_token": 5e-06, @@ -38631,30 +38649,36 @@ "openrouter/openai/o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/openai/o3-mini" }, "openrouter/openai/o3-mini-high": { "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/openai/o3-mini-high" }, "openrouter/qwen/qwen-2.5-coder-32b-instruct": { "input_cost_per_token": 1.8e-07, @@ -39672,21 +39696,33 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": true, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.4e-05, + "cache_read_input_token_cost": 1.75e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.1": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 2.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-6": { "supports_adaptive_thinking": true, @@ -39696,7 +39732,11 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-7": { "supports_adaptive_thinking": true, @@ -39705,7 +39745,11 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", @@ -39713,21 +39757,33 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-haiku-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3-pro-preview": { "litellm_provider": "perplexity", @@ -39741,7 +39797,11 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-2.5-pro": { "litellm_provider": "perplexity", @@ -39770,7 +39830,11 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 6.25e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 2.8e-08, @@ -59010,5 +59074,892 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ] + }, + "gemini/lyria-3.5-clip-preview": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_image": 0.04, + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false + }, + "gemini/lyria-3.5-pro-preview": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "output_cost_per_image": 0.08 + }, + "perplexity/anthropic/claude-fable-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-4-8": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-sonnet-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-sonnet-4-6": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-terra": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_above_272k_tokens": 4e-07, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_above_272k_tokens": 5e-06, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4-mini": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 4.5e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4-nano": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.1-pro-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.1-flash-lite": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 2.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.5-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "cache_read_input_token_cost": 1.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.5-flash-lite": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 3e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.6-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.7-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.6": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.3": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-non-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-multi-agent": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "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, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/glm-5.3": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/glm-5.3-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 3e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/nemotron-3.5-lightning-30b-a3b": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.15e-08, + "output_cost_per_token": 1.7e-07, + "cache_read_input_token_cost": 1.15e-09, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "openrouter/anthropic/claude-fable-5": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-fable-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1e-06, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 1.25e-05 + }, + "openrouter/anthropic/claude-fable-5.1": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-fable-5.1", + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 1.25e-05 + }, + "openrouter/anthropic/claude-opus-4.8": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-opus-4.8", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 6.25e-06 + }, + "openrouter/anthropic/claude-sonnet-5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/anthropic/claude-sonnet-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 2.5e-06 + }, + "openrouter/google/gemini-2.5-flash-lite": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-flash-lite", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.5-flash": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.5-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.5-flash-lite": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.5-flash-lite", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 3e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.6-flash": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.6-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.7-flash": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.7-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3.8-flash": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.8-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.1": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1.25e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.3-codex": { + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.4e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.3-codex", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1.75e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.4": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.4-mini": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 4.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.4-nano": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4-nano", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.5": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.6-luna": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.6-luna", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.6-terra": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.6-terra", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/o3": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true + }, + "openrouter/openai/o4-mini": { + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o4-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.75e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.20": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.20", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.20-multi-agent": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.20-multi-agent", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.3": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 900000, + "max_tokens": 900000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 3e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-4.6": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-4.6", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true + }, + "openrouter/x-ai/grok-build-0.1": { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 230400, + "max_tokens": 230400, + "mode": "chat", + "source": "https://openrouter.ai/x-ai/grok-build-0.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true } } From 2c4eb693ed92a1fe933794b3c8cf3cc0e6b905d9 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 19:53:58 +0000 Subject: [PATCH 11/23] fix(model_prices): absorb Baseten GLM-5.3 and OpenRouter live prices, fix Bedrock Qwen3 Coder 480B input price and Gemini Live image price Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 253 ++++++++++-------- model_prices_and_context_window.json | 253 ++++++++++-------- .../test_get_model_cost_map.py | 52 +++- .../test_baseten_glm_5_3_model_metadata.py | 154 +++++++++++ tests/test_litellm/test_utils.py | 8 +- 5 files changed, 487 insertions(+), 233 deletions(-) create mode 100644 tests/test_litellm/test_baseten_glm_5_3_model_metadata.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 724929a48f5..a6f3095e974 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -22968,7 +22968,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "gemini_native_audio": true + "gemini_native_audio": true, + "input_cost_per_image_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "cache_read_input_token_cost": 7.5e-08, @@ -37637,7 +37638,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -37733,24 +37734,24 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 1.4e-07, + "input_cost_per_token": 3.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "output_cost_per_token": 8.9e-07, "supports_prompt_caching": true, "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 1.4e-07, + "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "output_cost_per_token": 1e-06, "supports_prompt_caching": true, "supports_tool_choice": true }, @@ -37770,7 +37771,7 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v3.2": { - "input_cost_per_token": 2.8e-07, + "input_cost_per_token": 2.69e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, @@ -37785,14 +37786,14 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v3.2-exp": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 2.7e-07, "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 4e-07, + "output_cost_per_token": 4.1e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -37800,14 +37801,14 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-r1": { - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 7e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.19e-06, + "output_cost_per_token": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -37903,8 +37904,8 @@ "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_output": true, @@ -38119,19 +38120,19 @@ "supports_vision": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 1.875e-06, + "input_cost_per_token": 6e-08, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.875e-06, + "output_cost_per_token": 6e-08, "supports_tool_choice": true }, "openrouter/mancer/weaver": { - "input_cost_per_token": 5.625e-06, + "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", "max_tokens": 2000, "mode": "chat", - "output_cost_per_token": 5.625e-06, + "output_cost_per_token": 7.5e-07, "supports_tool_choice": true, "max_input_tokens": 8000, "max_output_tokens": 2000 @@ -38161,13 +38162,13 @@ }, "openrouter/mistralai/devstral-2512": { "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, @@ -38240,54 +38241,54 @@ "max_output_tokens": 8191 }, "openrouter/mistralai/mistral-large": { - "input_cost_per_token": 8e-06, + "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 6e-06, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 8191 }, "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 3.51e-07, "litellm_provider": "openrouter", "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 5.55e-07, "supports_tool_choice": true, "max_input_tokens": 131072, "max_output_tokens": 131072 }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 2e-07, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 128000 }, "openrouter/mistralai/mixtral-8x22b-instruct": { - "input_cost_per_token": 6.5e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 6.5e-07, + "output_cost_per_token": 6e-06, "supports_tool_choice": true, "max_input_tokens": 65536, "max_output_tokens": 65536 }, "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 2.25e-06, "source": "https://openrouter.ai/moonshotai/kimi-k2.5", "supports_function_calling": true, "supports_tool_choice": true, @@ -38295,7 +38296,7 @@ "supports_vision": true }, "openrouter/nvidia/nemotron-3.5-lightning": { - "input_cost_per_token": 5e-08, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "mode": "chat", @@ -38600,13 +38601,13 @@ "supports_vision": true }, "openrouter/openai/gpt-oss-120b": { - "input_cost_per_token": 1.8e-07, + "input_cost_per_token": 3.7e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 1.7e-07, "source": "https://openrouter.ai/openai/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -38615,13 +38616,13 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-oss-20b": { - "input_cost_per_token": 2e-08, + "input_cost_per_token": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 1.3e-07, "source": "https://openrouter.ai/openai/gpt-oss-20b", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -38681,13 +38682,13 @@ "source": "https://openrouter.ai/openai/o3-mini-high" }, "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 1.8e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "openrouter", "max_input_tokens": 33792, "max_output_tokens": 33792, "max_tokens": 33792, "mode": "chat", - "output_cost_per_token": 1.8e-07, + "output_cost_per_token": 1e-06, "supports_tool_choice": true }, "openrouter/qwen/qwen-vl-plus": { @@ -38702,50 +38703,50 @@ "supports_vision": true }, "openrouter/qwen/qwen3-coder": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262100, "max_output_tokens": 262100, "max_tokens": 262100, "mode": "chat", - "output_cost_per_token": 9.5e-07, + "output_cost_per_token": 1e-06, "source": "https://openrouter.ai/qwen/qwen3-coder", "supports_tool_choice": true, "supports_function_calling": true }, "openrouter/qwen/qwen3-coder-plus": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 6.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5e-06, + "output_cost_per_token": 3.25e-06, "source": "https://openrouter.ai/qwen/qwen3-coder-plus", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 7.1e-08, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 3.5e-07, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 1.1e-07, + "input_cost_per_token": 2.3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 2.3e-06, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", "supports_function_calling": true, "supports_reasoning": true, @@ -38772,7 +38773,7 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1.25e-06, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, @@ -38780,13 +38781,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 1.95e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.56e-06, "source": "https://openrouter.ai/qwen/qwen3.5-27b", "supports_function_calling": true, "supports_reasoning": true, @@ -38794,13 +38795,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 2.9e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 2.4e-06, "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", "supports_function_calling": true, "supports_reasoning": true, @@ -38808,13 +38809,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4e-07, + "output_cost_per_token": 2.6e-07, "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23", "supports_function_calling": true, "supports_reasoning": true, @@ -38822,14 +38823,14 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 2.6e-07, "input_cost_per_token_above_256k_tokens": 5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.56e-06, "output_cost_per_token_above_256k_tokens": 3e-06, "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15", "supports_function_calling": true, @@ -38838,13 +38839,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-397b-a17b": { - "input_cost_per_token": 6e-07, + "input_cost_per_token": 5.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3.6e-06, + "output_cost_per_token": 3.5e-06, "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", "supports_function_calling": true, "supports_reasoning": true, @@ -38863,11 +38864,11 @@ "supports_tool_choice": true }, "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 1.875e-06, + "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.875e-06, + "output_cost_per_token": 6.5e-07, "supports_tool_choice": true, "max_input_tokens": 6144, "max_output_tokens": 4096 @@ -38887,13 +38888,13 @@ "supports_web_search": true }, "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 5.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 1.75e-06, + "output_cost_per_token": 2.2e-06, "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_function_calling": true, "supports_prompt_caching": true, @@ -38931,10 +38932,10 @@ "supports_prompt_caching": true }, "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 3.6e-09, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 16384, @@ -38948,10 +38949,10 @@ "supports_prompt_caching": true }, "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 8e-08, + "cache_read_input_token_cost": 2.8e-09, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, @@ -38968,9 +38969,9 @@ }, "openrouter/z-ai/glm-4.7": { "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.5e-06, + "output_cost_per_token": 1.75e-06, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 8e-08, "litellm_provider": "openrouter", "max_input_tokens": 202752, "max_output_tokens": 64000, @@ -38984,10 +38985,10 @@ "supports_assistant_prefill": true }, "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 7e-08, + "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-08, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 32000, @@ -39000,22 +39001,22 @@ "supports_prompt_caching": false }, "openrouter/z-ai/glm-5": { - "input_cost_per_token": 8e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "openrouter", "max_input_tokens": 202752, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.56e-06, + "output_cost_per_token": 1.92e-06, "source": "https://openrouter.ai/z-ai/glm-5", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "openrouter/z-ai/glm-5.1": { - "input_cost_per_token": 1.05e-06, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 5.25e-07, + "input_cost_per_token": 9.66e-07, + "output_cost_per_token": 3.036e-06, + "cache_read_input_token_cost": 1.794e-07, "cache_creation_input_token_cost": 0.0, "litellm_provider": "openrouter", "max_input_tokens": 202752, @@ -39029,10 +39030,10 @@ "supports_tool_choice": true }, "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 2.7e-07, + "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 204000, "max_output_tokens": 64000, @@ -39046,9 +39047,9 @@ "supports_computer_use": false }, "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.1e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 1.08e-06, + "cache_read_input_token_cost": 2.7e-08, "litellm_provider": "openrouter", "max_input_tokens": 196608, "max_output_tokens": 65536, @@ -39947,7 +39948,7 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262000, "max_output_tokens": 65536, @@ -39957,7 +39958,8 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, @@ -52852,7 +52854,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52878,7 +52880,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52904,7 +52906,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52932,7 +52934,7 @@ "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52963,7 +52965,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52991,7 +52993,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -53019,7 +53021,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -53049,7 +53051,7 @@ "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -59463,7 +59465,8 @@ "supports_audio_input": false, "cache_read_input_token_cost": 1e-06, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05 + "cache_creation_input_token_cost": 1.25e-05, + "prompt_cache_min_tokens": 512 }, "openrouter/anthropic/claude-fable-5.1": { "input_cost_per_token": 1e-05, @@ -59483,7 +59486,8 @@ "supports_audio_input": false, "cache_read_input_token_cost": 2.5e-07, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05 + "cache_creation_input_token_cost": 1.25e-05, + "prompt_cache_min_tokens": 512 }, "openrouter/anthropic/claude-opus-4.8": { "input_cost_per_token": 5e-06, @@ -59549,8 +59553,8 @@ "output_cost_per_token": 9e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "source": "https://openrouter.ai/google/gemini-3.5-flash", "supports_function_calling": true, @@ -59662,7 +59666,7 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59681,7 +59685,7 @@ "input_cost_per_token": 1.75e-06, "output_cost_per_token": 1.4e-05, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59719,7 +59723,7 @@ "input_cost_per_token": 7.5e-07, "output_cost_per_token": 4.5e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59738,7 +59742,7 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59776,7 +59780,7 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59795,7 +59799,7 @@ "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59852,9 +59856,9 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.20", "supports_function_calling": true, @@ -59871,9 +59875,9 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.20-multi-agent", "supports_function_calling": false, @@ -59891,8 +59895,8 @@ "output_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.3", "supports_function_calling": true, @@ -59910,8 +59914,8 @@ "output_cost_per_token": 6e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.5", "supports_function_calling": true, @@ -59929,8 +59933,8 @@ "output_cost_per_token": 6e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.6", "supports_function_calling": true, @@ -59948,8 +59952,8 @@ "output_cost_per_token": 2e-06, "litellm_provider": "openrouter", "max_input_tokens": 256000, - "max_output_tokens": 230400, - "max_tokens": 230400, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-build-0.1", "supports_function_calling": true, @@ -59961,5 +59965,26 @@ "supports_audio_input": false, "cache_read_input_token_cost": 2e-07, "supports_prompt_caching": true + }, + "baseten/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.baseten.co/pricing/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 724929a48f5..a6f3095e974 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -22968,7 +22968,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "gemini_native_audio": true + "gemini_native_audio": true, + "input_cost_per_image_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "cache_read_input_token_cost": 7.5e-08, @@ -37637,7 +37638,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -37733,24 +37734,24 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 1.4e-07, + "input_cost_per_token": 3.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "output_cost_per_token": 8.9e-07, "supports_prompt_caching": true, "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 1.4e-07, + "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "output_cost_per_token": 1e-06, "supports_prompt_caching": true, "supports_tool_choice": true }, @@ -37770,7 +37771,7 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v3.2": { - "input_cost_per_token": 2.8e-07, + "input_cost_per_token": 2.69e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, @@ -37785,14 +37786,14 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v3.2-exp": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 2.7e-07, "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 4e-07, + "output_cost_per_token": 4.1e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -37800,14 +37801,14 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-r1": { - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 7e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.19e-06, + "output_cost_per_token": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -37903,8 +37904,8 @@ "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_output": true, @@ -38119,19 +38120,19 @@ "supports_vision": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 1.875e-06, + "input_cost_per_token": 6e-08, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.875e-06, + "output_cost_per_token": 6e-08, "supports_tool_choice": true }, "openrouter/mancer/weaver": { - "input_cost_per_token": 5.625e-06, + "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", "max_tokens": 2000, "mode": "chat", - "output_cost_per_token": 5.625e-06, + "output_cost_per_token": 7.5e-07, "supports_tool_choice": true, "max_input_tokens": 8000, "max_output_tokens": 2000 @@ -38161,13 +38162,13 @@ }, "openrouter/mistralai/devstral-2512": { "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, @@ -38240,54 +38241,54 @@ "max_output_tokens": 8191 }, "openrouter/mistralai/mistral-large": { - "input_cost_per_token": 8e-06, + "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 6e-06, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 8191 }, "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 3.51e-07, "litellm_provider": "openrouter", "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 5.55e-07, "supports_tool_choice": true, "max_input_tokens": 131072, "max_output_tokens": 131072 }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 2e-07, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 128000 }, "openrouter/mistralai/mixtral-8x22b-instruct": { - "input_cost_per_token": 6.5e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 6.5e-07, + "output_cost_per_token": 6e-06, "supports_tool_choice": true, "max_input_tokens": 65536, "max_output_tokens": 65536 }, "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 2.25e-06, "source": "https://openrouter.ai/moonshotai/kimi-k2.5", "supports_function_calling": true, "supports_tool_choice": true, @@ -38295,7 +38296,7 @@ "supports_vision": true }, "openrouter/nvidia/nemotron-3.5-lightning": { - "input_cost_per_token": 5e-08, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "mode": "chat", @@ -38600,13 +38601,13 @@ "supports_vision": true }, "openrouter/openai/gpt-oss-120b": { - "input_cost_per_token": 1.8e-07, + "input_cost_per_token": 3.7e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 1.7e-07, "source": "https://openrouter.ai/openai/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -38615,13 +38616,13 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-oss-20b": { - "input_cost_per_token": 2e-08, + "input_cost_per_token": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 1.3e-07, "source": "https://openrouter.ai/openai/gpt-oss-20b", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -38681,13 +38682,13 @@ "source": "https://openrouter.ai/openai/o3-mini-high" }, "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 1.8e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "openrouter", "max_input_tokens": 33792, "max_output_tokens": 33792, "max_tokens": 33792, "mode": "chat", - "output_cost_per_token": 1.8e-07, + "output_cost_per_token": 1e-06, "supports_tool_choice": true }, "openrouter/qwen/qwen-vl-plus": { @@ -38702,50 +38703,50 @@ "supports_vision": true }, "openrouter/qwen/qwen3-coder": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262100, "max_output_tokens": 262100, "max_tokens": 262100, "mode": "chat", - "output_cost_per_token": 9.5e-07, + "output_cost_per_token": 1e-06, "source": "https://openrouter.ai/qwen/qwen3-coder", "supports_tool_choice": true, "supports_function_calling": true }, "openrouter/qwen/qwen3-coder-plus": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 6.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5e-06, + "output_cost_per_token": 3.25e-06, "source": "https://openrouter.ai/qwen/qwen3-coder-plus", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 7.1e-08, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 3.5e-07, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 1.1e-07, + "input_cost_per_token": 2.3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 2.3e-06, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", "supports_function_calling": true, "supports_reasoning": true, @@ -38772,7 +38773,7 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1.25e-06, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, @@ -38780,13 +38781,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 1.95e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.56e-06, "source": "https://openrouter.ai/qwen/qwen3.5-27b", "supports_function_calling": true, "supports_reasoning": true, @@ -38794,13 +38795,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 2.9e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 2.4e-06, "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", "supports_function_calling": true, "supports_reasoning": true, @@ -38808,13 +38809,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4e-07, + "output_cost_per_token": 2.6e-07, "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23", "supports_function_calling": true, "supports_reasoning": true, @@ -38822,14 +38823,14 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 2.6e-07, "input_cost_per_token_above_256k_tokens": 5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.56e-06, "output_cost_per_token_above_256k_tokens": 3e-06, "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15", "supports_function_calling": true, @@ -38838,13 +38839,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-397b-a17b": { - "input_cost_per_token": 6e-07, + "input_cost_per_token": 5.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3.6e-06, + "output_cost_per_token": 3.5e-06, "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", "supports_function_calling": true, "supports_reasoning": true, @@ -38863,11 +38864,11 @@ "supports_tool_choice": true }, "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 1.875e-06, + "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.875e-06, + "output_cost_per_token": 6.5e-07, "supports_tool_choice": true, "max_input_tokens": 6144, "max_output_tokens": 4096 @@ -38887,13 +38888,13 @@ "supports_web_search": true }, "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 5.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 1.75e-06, + "output_cost_per_token": 2.2e-06, "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_function_calling": true, "supports_prompt_caching": true, @@ -38931,10 +38932,10 @@ "supports_prompt_caching": true }, "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 3.6e-09, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 16384, @@ -38948,10 +38949,10 @@ "supports_prompt_caching": true }, "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 8e-08, + "cache_read_input_token_cost": 2.8e-09, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, @@ -38968,9 +38969,9 @@ }, "openrouter/z-ai/glm-4.7": { "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.5e-06, + "output_cost_per_token": 1.75e-06, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 8e-08, "litellm_provider": "openrouter", "max_input_tokens": 202752, "max_output_tokens": 64000, @@ -38984,10 +38985,10 @@ "supports_assistant_prefill": true }, "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 7e-08, + "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-08, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 32000, @@ -39000,22 +39001,22 @@ "supports_prompt_caching": false }, "openrouter/z-ai/glm-5": { - "input_cost_per_token": 8e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "openrouter", "max_input_tokens": 202752, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.56e-06, + "output_cost_per_token": 1.92e-06, "source": "https://openrouter.ai/z-ai/glm-5", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "openrouter/z-ai/glm-5.1": { - "input_cost_per_token": 1.05e-06, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 5.25e-07, + "input_cost_per_token": 9.66e-07, + "output_cost_per_token": 3.036e-06, + "cache_read_input_token_cost": 1.794e-07, "cache_creation_input_token_cost": 0.0, "litellm_provider": "openrouter", "max_input_tokens": 202752, @@ -39029,10 +39030,10 @@ "supports_tool_choice": true }, "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 2.7e-07, + "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 204000, "max_output_tokens": 64000, @@ -39046,9 +39047,9 @@ "supports_computer_use": false }, "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.1e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 1.08e-06, + "cache_read_input_token_cost": 2.7e-08, "litellm_provider": "openrouter", "max_input_tokens": 196608, "max_output_tokens": 65536, @@ -39947,7 +39948,7 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262000, "max_output_tokens": 65536, @@ -39957,7 +39958,8 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, @@ -52852,7 +52854,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52878,7 +52880,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52904,7 +52906,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52932,7 +52934,7 @@ "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52963,7 +52965,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -52991,7 +52993,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -53019,7 +53021,7 @@ "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -53049,7 +53051,7 @@ "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -59463,7 +59465,8 @@ "supports_audio_input": false, "cache_read_input_token_cost": 1e-06, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05 + "cache_creation_input_token_cost": 1.25e-05, + "prompt_cache_min_tokens": 512 }, "openrouter/anthropic/claude-fable-5.1": { "input_cost_per_token": 1e-05, @@ -59483,7 +59486,8 @@ "supports_audio_input": false, "cache_read_input_token_cost": 2.5e-07, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05 + "cache_creation_input_token_cost": 1.25e-05, + "prompt_cache_min_tokens": 512 }, "openrouter/anthropic/claude-opus-4.8": { "input_cost_per_token": 5e-06, @@ -59549,8 +59553,8 @@ "output_cost_per_token": 9e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "source": "https://openrouter.ai/google/gemini-3.5-flash", "supports_function_calling": true, @@ -59662,7 +59666,7 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59681,7 +59685,7 @@ "input_cost_per_token": 1.75e-06, "output_cost_per_token": 1.4e-05, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59719,7 +59723,7 @@ "input_cost_per_token": 7.5e-07, "output_cost_per_token": 4.5e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59738,7 +59742,7 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59776,7 +59780,7 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59795,7 +59799,7 @@ "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -59852,9 +59856,9 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.20", "supports_function_calling": true, @@ -59871,9 +59875,9 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.20-multi-agent", "supports_function_calling": false, @@ -59891,8 +59895,8 @@ "output_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.3", "supports_function_calling": true, @@ -59910,8 +59914,8 @@ "output_cost_per_token": 6e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.5", "supports_function_calling": true, @@ -59929,8 +59933,8 @@ "output_cost_per_token": 6e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-4.6", "supports_function_calling": true, @@ -59948,8 +59952,8 @@ "output_cost_per_token": 2e-06, "litellm_provider": "openrouter", "max_input_tokens": 256000, - "max_output_tokens": 230400, - "max_tokens": 230400, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", "source": "https://openrouter.ai/x-ai/grok-build-0.1", "supports_function_calling": true, @@ -59961,5 +59965,26 @@ "supports_audio_input": false, "cache_read_input_token_cost": 2e-07, "supports_prompt_caching": true + }, + "baseten/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.baseten.co/pricing/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true } } 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 a374e03d1c7..18185126775 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 @@ -9,7 +9,6 @@ import os import pytest - from litellm.litellm_core_utils.fallback_generalizations import ( get_fallback_generalization_rules, match_capability_generalizations, @@ -248,6 +247,57 @@ def test_azure_ai_claude_1m_context_entries(cost_map: dict): assert cost_map[model]["max_input_tokens"] == 200000, model +# OpenRouter headline rates from GET https://openrouter.ai/api/v1/models. +# These were the catalog values that disagreed with that API (and, for the +# two spotlight models, the public model pages that their source fields cite). +_OPENROUTER_LIVE_COSTS = { + "openrouter/qwen/qwen3.5-plus-02-15": (2.6e-07, 1.56e-06, None), + "openrouter/openai/gpt-oss-120b": (3.7e-08, 1.7e-07, None), + "openrouter/qwen/qwen3-coder-plus": (6.5e-07, 3.25e-06, None), + "openrouter/qwen/qwen3.5-flash-02-23": (6.5e-08, 2.6e-07, None), + "openrouter/qwen/qwen3.5-27b": (1.95e-07, 1.56e-06, None), + "openrouter/gryphe/mythomax-l2-13b": (6e-08, 6e-08, None), + "openrouter/mancer/weaver": (4e-07, 7.5e-07, None), + "openrouter/xiaomi/mimo-v2.5-pro": (4.35e-07, 8.7e-07, 3.6e-09), + "openrouter/moonshotai/kimi-k2.5": (4.5e-07, 2.25e-06, 7e-08), + "openrouter/z-ai/glm-5": (6e-07, 1.92e-06, None), +} + +_OPENROUTER_STALE_COSTS = { + "openrouter/qwen/qwen3.5-plus-02-15": (4e-07, 2.4e-06), + "openrouter/openai/gpt-oss-120b": (1.8e-07, 8e-07), + "openrouter/gryphe/mythomax-l2-13b": (1.875e-06, 1.875e-06), +} + + +@pytest.mark.parametrize( + "cost_map", + [_load_root_cost_map(), GetModelCostMap.load_local_model_cost_map()], + ids=["root", "bundled_backup"], +) +def test_openrouter_catalog_costs_match_live_headline_rates(cost_map: dict): + """openrouter/* spend tracking reads these catalog fields. The values must + stay aligned with OpenRouter's published headline rate, not the stale + figures that over/under-counted by up to 30x. Both maps are checked so + the root file and bundled backup cannot drift apart.""" + control = cost_map["openrouter/anthropic/claude-opus-5"] + assert control["input_cost_per_token"] == 5e-06 + assert control["output_cost_per_token"] == 2.5e-05 + assert control["cache_read_input_token_cost"] == 5e-07 + + for model, (inp, out, cache) in _OPENROUTER_LIVE_COSTS.items(): + entry = cost_map[model] + assert entry["input_cost_per_token"] == inp, model + assert entry["output_cost_per_token"] == out, model + if cache is not None: + assert entry["cache_read_input_token_cost"] == cache, model + + for model, (stale_in, stale_out) in _OPENROUTER_STALE_COSTS.items(): + entry = cost_map[model] + assert entry["input_cost_per_token"] != stale_in, model + assert entry["output_cost_per_token"] != stale_out, model + + def test_get_model_cost_map_stamps_loaded_at(monkeypatch): """The load time feeds each pod's reload-due decision; a load that does not stamp it would make manual reload requests race the proxy's startup""" diff --git a/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py b/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py new file mode 100644 index 00000000000..98a8cf026ec --- /dev/null +++ b/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py @@ -0,0 +1,154 @@ +import json +from pathlib import Path + +import pytest + +import litellm +from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider +from litellm.types.utils import PromptTokensDetailsWrapper, Usage +from litellm.utils import supports_function_calling, supports_prompt_caching + +REPO_ROOT = Path(__file__).parents[2] +MAIN_PATH = REPO_ROOT / "model_prices_and_context_window.json" +BACKUP_PATH = REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json" + +MODEL = "baseten/zai-org/GLM-5.3" + +INPUT_COST = 1.4e-06 +CACHED_INPUT_COST = 1.4e-07 +OUTPUT_COST = 4.4e-06 + + +def _load(path): + with open(path) as f: + return json.load(f) + + +@pytest.fixture +def local_model_cost_map(monkeypatch): + """Force get_model_info to resolve against the in-repo cost map instead of the + remote one fetched at import time, which still carries the pre-merge registry.""" + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + litellm.get_model_info.cache_clear() + yield + litellm.get_model_info.cache_clear() + + +def test_baseten_glm_5_3_specs(): + info = _load(MAIN_PATH).get(MODEL) + assert info is not None, f"{MODEL} missing from model_prices_and_context_window.json" + + assert info["litellm_provider"] == "baseten" + assert info["mode"] == "chat" + + assert info["input_cost_per_token"] == INPUT_COST + assert info["output_cost_per_token"] == OUTPUT_COST + assert info["cache_read_input_token_cost"] == CACHED_INPUT_COST + + assert info["max_input_tokens"] == 1048576 + assert info["max_output_tokens"] == 262144 + assert info["max_tokens"] == 262144 + + assert info["supports_function_calling"] is True + assert info["supports_prompt_caching"] is True + assert info["supports_response_schema"] is True + assert info["supports_tool_choice"] is True + assert info["supported_modalities"] == ["text"] + assert info["supported_output_modalities"] == ["text"] + + routed_model, provider, _, _ = get_llm_provider(model=MODEL) + assert routed_model == "zai-org/GLM-5.3" + assert provider == "baseten" + + +def test_baseten_glm_5_3_capabilities_are_visible_to_callers(local_model_cost_map): + """The entry advertises prompt caching and tool calling, so the helpers every + caller checks before sending a request must say so too.""" + assert supports_prompt_caching(model=MODEL) is True + assert supports_function_calling(model=MODEL) is True + + info = litellm.get_model_info(model="zai-org/GLM-5.3", custom_llm_provider="baseten") + assert info["max_input_tokens"] == 1048576 + assert info["max_output_tokens"] == 262144 + + +def test_cached_prompt_tokens_bill_at_the_cached_rate(local_model_cost_map): + """A cache hit reports its reused tokens under prompt_tokens_details, and those + tokens cost a tenth of the input rate, not the full rate and not nothing.""" + usage = Usage( + prompt_tokens=21010, + completion_tokens=100, + total_tokens=21110, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=20992), + ) + + prompt_cost, completion_cost = litellm.cost_per_token( + model=MODEL, usage_object=usage, custom_llm_provider="baseten" + ) + + assert prompt_cost == pytest.approx(18 * INPUT_COST + 20992 * CACHED_INPUT_COST) + assert completion_cost == pytest.approx(100 * OUTPUT_COST) + + +def test_backup_matches_main(): + """Ensure the bundled (backup) cost map stays in sync with the canonical file. + + Both keys are asserted present first: comparing two ``.get`` results alone passes + just as happily when neither file has the entry at all, which is the exact state + this test exists to catch. + """ + main_cost = _load(MAIN_PATH) + backup_cost = _load(BACKUP_PATH) + + assert MODEL in main_cost, f"{MODEL} missing from model_prices_and_context_window.json" + assert MODEL in backup_cost, f"{MODEL} missing from model_prices_and_context_window_backup.json" + assert backup_cost[MODEL] == main_cost[MODEL], f"{MODEL} differs between main and backup model cost maps" + + +def test_entry_advertises_only_what_the_baseten_path_accepts(local_model_cost_map): + """The entry must not claim a capability whose request parameter BasetenConfig + refuses. + + ``BasetenConfig.get_supported_openai_params`` returns one hardcoded list for every + Baseten model, and it carries neither ``parallel_tool_calls`` nor + ``reasoning_effort``. Baseten's own Model API does take ``reasoning_effort``, but + litellm's Baseten path drops it (``drop_params=True``) or raises + ``UnsupportedParamsError`` (``drop_params=False``), so declaring + ``supports_parallel_function_calling``, ``supports_reasoning`` or + ``reasoning_effort_levels`` here would advertise a level the gateway then refuses to + send. Wiring those params through the Baseten config is separate work; until it + lands, the registry stays honest. + """ + supported = litellm.get_supported_openai_params(model="zai-org/GLM-5.3", custom_llm_provider="baseten") + assert supported is not None + + entry = _load(MAIN_PATH)[MODEL] + + capability_to_param = { + "supports_function_calling": "tools", + "supports_tool_choice": "tool_choice", + "supports_response_schema": "response_format", + "supports_parallel_function_calling": "parallel_tool_calls", + "supports_reasoning": "reasoning_effort", + } + for capability, param in capability_to_param.items(): + if entry.get(capability): + assert param in supported, f"{MODEL} advertises {capability} but baseten drops/rejects {param}" + + assert "reasoning_effort_levels" not in entry, ( + "reasoning_effort_levels advertises accepted reasoning_effort values, which the Baseten path does not accept" + ) + assert "thinking_always_on" not in entry, ( + "thinking_always_on is only read by AnthropicModelInfo._is_always_on_thinking_model, " + "which no Baseten route reaches" + ) + + with pytest.raises(litellm.UnsupportedParamsError): + litellm.utils.get_optional_params( + model="zai-org/GLM-5.3", + custom_llm_provider="baseten", + parallel_tool_calls=True, + reasoning_effort="high", + drop_params=False, + ) diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 99c69d6bc31..5575c4328a2 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -2779,7 +2779,7 @@ def test_model_info_for_openrouter_kimi_k2_5(): Model properties from OpenRouter API: - context_length: 262144 - - pricing: prompt=$0.0000006, completion=$0.000003, input_cache_read=$0.0000001 + - pricing: prompt=$0.00000045, completion=$0.00000225, input_cache_read=$0.00000007 - modality: text+image->text (supports vision) - supports: tool_choice, tools (function calling) """ @@ -2804,9 +2804,9 @@ def test_model_info_for_openrouter_kimi_k2_5(): assert model_info["max_tokens"] == 262144 # Verify pricing - assert model_info["input_cost_per_token"] == 6e-07 - assert model_info["output_cost_per_token"] == 3e-06 - assert model_info["cache_read_input_token_cost"] == 1e-07 + assert model_info["input_cost_per_token"] == 4.5e-07 + assert model_info["output_cost_per_token"] == 2.25e-06 + assert model_info["cache_read_input_token_cost"] == 7e-08 # Verify capabilities assert model_info["supports_vision"] is True From 080e364d5ec1248a0d045af13732024c1654d642 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 20:28:48 +0000 Subject: [PATCH 12/23] fix(registry): carry Anthropic thinking/sampling flags on new Perplexity and OpenRouter Claude entries Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../model_prices_and_context_window_backup.json | 16 ++++++++++++++++ model_prices_and_context_window.json | 16 ++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a6f3095e974..260a9c3a34e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -59130,6 +59130,8 @@ "perplexity/anthropic/claude-fable-5": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1e-05, @@ -59140,6 +59142,8 @@ "perplexity/anthropic/claude-opus-5": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, @@ -59150,6 +59154,7 @@ "perplexity/anthropic/claude-opus-4-8": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, @@ -59160,6 +59165,7 @@ "perplexity/anthropic/claude-sonnet-5": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, @@ -59455,6 +59461,9 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, "source": "https://openrouter.ai/anthropic/claude-fable-5", "supports_function_calling": true, "supports_tool_choice": true, @@ -59476,6 +59485,9 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, "source": "https://openrouter.ai/anthropic/claude-fable-5.1", "supports_function_calling": true, "supports_tool_choice": false, @@ -59497,6 +59509,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, "source": "https://openrouter.ai/anthropic/claude-opus-4.8", "supports_function_calling": true, "supports_tool_choice": true, @@ -59517,6 +59531,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, "source": "https://openrouter.ai/anthropic/claude-sonnet-5", "supports_function_calling": true, "supports_tool_choice": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a6f3095e974..260a9c3a34e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -59130,6 +59130,8 @@ "perplexity/anthropic/claude-fable-5": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1e-05, @@ -59140,6 +59142,8 @@ "perplexity/anthropic/claude-opus-5": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, @@ -59150,6 +59154,7 @@ "perplexity/anthropic/claude-opus-4-8": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, @@ -59160,6 +59165,7 @@ "perplexity/anthropic/claude-sonnet-5": { "litellm_provider": "perplexity", "mode": "responses", + "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, @@ -59455,6 +59461,9 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, "source": "https://openrouter.ai/anthropic/claude-fable-5", "supports_function_calling": true, "supports_tool_choice": true, @@ -59476,6 +59485,9 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, "source": "https://openrouter.ai/anthropic/claude-fable-5.1", "supports_function_calling": true, "supports_tool_choice": false, @@ -59497,6 +59509,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, "source": "https://openrouter.ai/anthropic/claude-opus-4.8", "supports_function_calling": true, "supports_tool_choice": true, @@ -59517,6 +59531,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, "source": "https://openrouter.ai/anthropic/claude-sonnet-5", "supports_function_calling": true, "supports_tool_choice": true, From eae7b806e3b71a8adc36e6d3a5bf0b51edaa7f97 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 20:49:44 +0000 Subject: [PATCH 13/23] fix(registry): point Bedrock Qwen3 Coder 480B source at the us-west-2 on-demand price list Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 2 +- model_prices_and_context_window.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 260a9c3a34e..3b6e7912253 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -39959,7 +39959,7 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 260a9c3a34e..3b6e7912253 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -39959,7 +39959,7 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, From 8d82f28c85bf4dec5c1701290b1d8aa8ebc58376 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 21:14:18 +0000 Subject: [PATCH 14/23] test(ocr): register the azure ocr4 mixed-rate cost test in the parity ledger Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../strategies/unit_tests/ledgers/ocr/ocr_test_ledger.json | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/rust-python-harness/strategies/unit_tests/ledgers/ocr/ocr_test_ledger.json b/tests/rust-python-harness/strategies/unit_tests/ledgers/ocr/ocr_test_ledger.json index 1ceb79b52bc..41381456993 100644 --- a/tests/rust-python-harness/strategies/unit_tests/ledgers/ocr/ocr_test_ledger.json +++ b/tests/rust-python-harness/strategies/unit_tests/ledgers/ocr/ocr_test_ledger.json @@ -146,6 +146,7 @@ {"python_file": "tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py", "python_test": "test_ocr3_bills_annotation_only_response", "status": "unmapped", "reason": "cost-calc: annotation-only billing math is Python-only"}, {"python_file": "tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py", "python_test": "test_ocr3_bills_annotation_pages_when_pages_processed_missing", "status": "unmapped", "reason": "cost-calc: fallback billing math is Python-only"}, {"python_file": "tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py", "python_test": "test_azure_doc_ai_annotation_pages_fall_back_to_ocr_rate", "status": "unmapped", "reason": "cost-calc: fallback billing math is Python-only"}, + {"python_file": "tests/test_litellm/llms/mistral/ocr/test_mistral_ocr_cost.py", "python_test": "test_azure_ocr4_bills_ocr_and_annotation_pages_at_their_own_rates", "status": "unmapped", "reason": "cost-calc: mixed-rate billing math is Python-only"}, {"python_file": "tests/test_litellm/ocr/test_ocr_native_format.py", "python_test": "test_rust_ocr_serves_default_format", "status": "unmapped", "reason": "request-format gating decision is made in Python before the Rust bridge is ever invoked"}, {"python_file": "tests/test_litellm/ocr/test_ocr_native_format.py", "python_test": "test_rust_ocr_skipped_for_native_format", "status": "unmapped", "reason": "request-format gating decision is made in Python before the Rust bridge is ever invoked"}, From 00bdfe797a385482bbfb66a167248eeee96ebf60 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 21:16:55 +0000 Subject: [PATCH 15/23] fix(registry): mark gemini-3.5-live-translate-preview as realtime with official token limits Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 8 ++++++-- model_prices_and_context_window.json | 8 ++++++-- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1c51385318b..682ad381268 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -55447,7 +55447,10 @@ "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", - "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, "rpm": 10, @@ -55459,7 +55462,8 @@ "audio" ], "supported_output_modalities": [ - "audio" + "audio", + "text" ], "supports_audio_input": true, "supports_audio_output": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1c51385318b..682ad381268 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -55447,7 +55447,10 @@ "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", - "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, "rpm": 10, @@ -55459,7 +55462,8 @@ "audio" ], "supported_output_modalities": [ - "audio" + "audio", + "text" ], "supports_audio_input": true, "supports_audio_output": true, From f29266760109252966e9b1739ceb6a9b97bac523 Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 3 Sep 2026 21:41:12 +0000 Subject: [PATCH 16/23] fix(registry): mark gpt-daybreak-*-latest as responses mode to match their Responses-only endpoints Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 4 ++-- model_prices_and_context_window.json | 4 ++-- tests/test_litellm/test_daybreak_model_metadata.py | 1 + 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 682ad381268..7f01d2322ff 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -29781,7 +29781,7 @@ "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", + "mode": "responses", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ @@ -29858,7 +29858,7 @@ "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", + "mode": "responses", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 682ad381268..7f01d2322ff 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -29781,7 +29781,7 @@ "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", + "mode": "responses", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ @@ -29858,7 +29858,7 @@ "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", + "mode": "responses", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ diff --git a/tests/test_litellm/test_daybreak_model_metadata.py b/tests/test_litellm/test_daybreak_model_metadata.py index 068bc01e103..dbb7ecdffac 100644 --- a/tests/test_litellm/test_daybreak_model_metadata.py +++ b/tests/test_litellm/test_daybreak_model_metadata.py @@ -62,6 +62,7 @@ def test_official_alias_tracks_snapshot(alias, snapshot): snapshot_info = cost_map[snapshot] assert alias_info["supported_endpoints"] == ["/v1/responses"] + assert alias_info["mode"] == "responses" assert alias_info["source"] == f"https://developers.openai.com/api/docs/models/{alias}" assert {field: alias_info.get(field) for field in PRICE_FIELDS} == { field: snapshot_info.get(field) for field in PRICE_FIELDS From 8e83d6d63d3d5bed593de08a2aab9da7c9dab0aa Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 14:06:54 +0000 Subject: [PATCH 17/23] fix(model_prices): add Databricks Sep-2026 catalog, Azure gpt-realtime-2.x, per-token realtime image pricing Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 733 +++++++++++++++++- model_prices_and_context_window.json | 733 +++++++++++++++++- .../llm_cost_calc/test_llm_cost_calc_utils.py | 22 + .../test_databricks_cost_calculator.py | 24 + 4 files changed, 1458 insertions(+), 54 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 616d58970cf..7304ca04eb5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -5311,7 +5311,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-03-02", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5344,7 +5344,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-08-24", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5372,11 +5372,115 @@ "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, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "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-mini": { + "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": "2027-06-25", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "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://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-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5408,7 +5512,7 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -16995,6 +17099,7 @@ "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", @@ -17042,6 +17147,35 @@ "supports_vision": false, "thinking_always_on": true }, + "databricks/databricks-claude-fable-5-1": { + "cache_creation_input_token_cost": 1.250004e-05, + "cache_read_input_token_cost": 2.5004e-07, + "input_cost_per_token": 1.000006e-05, + "input_dbu_cost_per_token": 0.000142858, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.000002e-05, + "output_dbu_cost_per_token": 0.000714286, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.0003e-07, @@ -17242,6 +17376,7 @@ "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-10-09", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -17254,13 +17389,13 @@ "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, + "prompt_cache_min_tokens": 1024, "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_tool_choice": true, - "prompt_cache_min_tokens": 1024 + "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { "cache_creation_input_token_cost": 3.74997e-06, @@ -17417,6 +17552,7 @@ "databricks/databricks-gemini-2-5-flash": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, + "deprecation_date": "2026-10-02", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", @@ -17474,6 +17610,48 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-1-flash-image": { + "litellm_provider": "databricks", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-3-pro-image": { + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, @@ -17534,6 +17712,148 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-8-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-7-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-6-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 9.37503e-06, + "output_dbu_cost_per_token": 0.000133929, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.124998e-05, + "output_dbu_cost_per_token": 0.000160714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash-lite": { + "cache_creation_input_token_cost": 3.7499e-07, + "cache_read_input_token_cost": 3.752e-08, + "input_cost_per_token": 3.7499e-07, + "input_dbu_cost_per_token": 5.357e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 3.12501e-06, + "output_dbu_cost_per_token": 4.4643e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, @@ -17579,16 +17899,53 @@ "supports_tool_choice": true, "supports_vision": false }, + "databricks/databricks-glm-5-3": { + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.5998e-07, + "input_cost_per_token": 1.4e-06, + "input_dbu_cost_per_token": 2e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.39999e-06, + "output_dbu_cost_per_token": 6.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, "databricks/databricks-glm-5-3-flash": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 3.003e-08, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { - "notes": "Databricks has not published pay-per-token DBU rates for this model yet (not on the foundation-model-serving pricing page as of 2026-08-27), so cost fields are omitted until rates are published." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" @@ -17600,7 +17957,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "thinking_always_on": true }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17618,7 +17976,9 @@ "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 + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17636,11 +17996,14 @@ "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 + "supports_function_calling": true, + "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", @@ -17659,6 +18022,7 @@ "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", @@ -17690,11 +18054,14 @@ "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 + "supports_function_calling": true, + "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", @@ -17726,7 +18093,9 @@ "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 + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, @@ -17734,7 +18103,7 @@ "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { @@ -17744,7 +18113,18 @@ "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_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, @@ -17762,7 +18142,18 @@ "output_cost_per_token": 4.50002e-06, "output_dbu_cost_per_token": 6.4286e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, @@ -17780,7 +18171,163 @@ "output_cost_per_token": 1.24999e-06, "output_dbu_cost_per_token": 1.7857e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-sol": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 3.9998e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-terra": { + "cache_creation_input_token_cost": 3.12501e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-luna": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.99998e-06, + "output_dbu_cost_per_token": 8.5714e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 2.999997e-05, + "output_dbu_cost_per_token": 0.000428571, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_dbu_cost_per_token": 0.000428571, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.00018000003, + "output_dbu_cost_per_token": 0.002571429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, @@ -17798,7 +18345,9 @@ "output_cost_per_token": 1.9999700000000004e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, @@ -17816,7 +18365,9 @@ "output_cost_per_token": 3.9998000000000007e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, @@ -17852,6 +18403,32 @@ "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-grok-4-6": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.000107143, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, @@ -17869,6 +18446,34 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-inkling": { + "cache_creation_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost": 1.7003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.04999e-06, + "output_dbu_cost_per_token": 5.7857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-kimi-k3": { "cache_creation_input_token_cost": 2.99999e-06, "cache_read_input_token_cost": 3.0002e-07, @@ -17901,6 +18506,7 @@ "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", @@ -17937,6 +18543,7 @@ "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", @@ -17990,6 +18597,7 @@ "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", @@ -18008,6 +18616,7 @@ "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", @@ -18026,6 +18635,7 @@ "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", @@ -18044,6 +18654,7 @@ "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", @@ -18059,6 +18670,74 @@ "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, + "input_cost_per_token": 2.2001e-07, + "input_dbu_cost_per_token": 3.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 262144, + "max_output_tokens": 25000, + "max_tokens": 25000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.20003e-06, + "output_dbu_cost_per_token": 3.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/databricks-qwen3-next-80b-a3b-instruct": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "databricks/databricks-qwen3-embedding-0-6b": { + "cache_creation_input_token_cost": 2.002e-08, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 2.002e-08, + "input_dbu_cost_per_token": 2.86e-07, + "litellm_provider": "databricks", + "max_input_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -31227,7 +31906,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31259,7 +31938,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31292,7 +31971,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31325,7 +32004,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31360,7 +32039,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31427,7 +32106,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -52723,7 +53402,7 @@ "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-07-23", "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -52756,7 +53435,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 616d58970cf..7304ca04eb5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -5311,7 +5311,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-03-02", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5344,7 +5344,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-08-24", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5372,11 +5372,115 @@ "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, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "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-mini": { + "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": "2027-06-25", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "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://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-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5408,7 +5512,7 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -16995,6 +17099,7 @@ "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", @@ -17042,6 +17147,35 @@ "supports_vision": false, "thinking_always_on": true }, + "databricks/databricks-claude-fable-5-1": { + "cache_creation_input_token_cost": 1.250004e-05, + "cache_read_input_token_cost": 2.5004e-07, + "input_cost_per_token": 1.000006e-05, + "input_dbu_cost_per_token": 0.000142858, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.000002e-05, + "output_dbu_cost_per_token": 0.000714286, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.0003e-07, @@ -17242,6 +17376,7 @@ "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-10-09", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -17254,13 +17389,13 @@ "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, + "prompt_cache_min_tokens": 1024, "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_tool_choice": true, - "prompt_cache_min_tokens": 1024 + "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { "cache_creation_input_token_cost": 3.74997e-06, @@ -17417,6 +17552,7 @@ "databricks/databricks-gemini-2-5-flash": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, + "deprecation_date": "2026-10-02", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", @@ -17474,6 +17610,48 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-1-flash-image": { + "litellm_provider": "databricks", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-3-pro-image": { + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, @@ -17534,6 +17712,148 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-8-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-7-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-6-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 9.37503e-06, + "output_dbu_cost_per_token": 0.000133929, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.124998e-05, + "output_dbu_cost_per_token": 0.000160714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash-lite": { + "cache_creation_input_token_cost": 3.7499e-07, + "cache_read_input_token_cost": 3.752e-08, + "input_cost_per_token": 3.7499e-07, + "input_dbu_cost_per_token": 5.357e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 3.12501e-06, + "output_dbu_cost_per_token": 4.4643e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, @@ -17579,16 +17899,53 @@ "supports_tool_choice": true, "supports_vision": false }, + "databricks/databricks-glm-5-3": { + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.5998e-07, + "input_cost_per_token": 1.4e-06, + "input_dbu_cost_per_token": 2e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.39999e-06, + "output_dbu_cost_per_token": 6.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, "databricks/databricks-glm-5-3-flash": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 3.003e-08, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { - "notes": "Databricks has not published pay-per-token DBU rates for this model yet (not on the foundation-model-serving pricing page as of 2026-08-27), so cost fields are omitted until rates are published." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" @@ -17600,7 +17957,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "thinking_always_on": true }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17618,7 +17976,9 @@ "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 + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17636,11 +17996,14 @@ "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 + "supports_function_calling": true, + "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", @@ -17659,6 +18022,7 @@ "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", @@ -17690,11 +18054,14 @@ "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 + "supports_function_calling": true, + "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", @@ -17726,7 +18093,9 @@ "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 + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, @@ -17734,7 +18103,7 @@ "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { @@ -17744,7 +18113,18 @@ "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_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, @@ -17762,7 +18142,18 @@ "output_cost_per_token": 4.50002e-06, "output_dbu_cost_per_token": 6.4286e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, @@ -17780,7 +18171,163 @@ "output_cost_per_token": 1.24999e-06, "output_dbu_cost_per_token": 1.7857e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-sol": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 3.9998e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-terra": { + "cache_creation_input_token_cost": 3.12501e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-luna": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.99998e-06, + "output_dbu_cost_per_token": 8.5714e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 2.999997e-05, + "output_dbu_cost_per_token": 0.000428571, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_dbu_cost_per_token": 0.000428571, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.00018000003, + "output_dbu_cost_per_token": 0.002571429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, @@ -17798,7 +18345,9 @@ "output_cost_per_token": 1.9999700000000004e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, @@ -17816,7 +18365,9 @@ "output_cost_per_token": 3.9998000000000007e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, @@ -17852,6 +18403,32 @@ "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-grok-4-6": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.000107143, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, @@ -17869,6 +18446,34 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-inkling": { + "cache_creation_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost": 1.7003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.04999e-06, + "output_dbu_cost_per_token": 5.7857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-kimi-k3": { "cache_creation_input_token_cost": 2.99999e-06, "cache_read_input_token_cost": 3.0002e-07, @@ -17901,6 +18506,7 @@ "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", @@ -17937,6 +18543,7 @@ "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", @@ -17990,6 +18597,7 @@ "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", @@ -18008,6 +18616,7 @@ "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", @@ -18026,6 +18635,7 @@ "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", @@ -18044,6 +18654,7 @@ "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", @@ -18059,6 +18670,74 @@ "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, + "input_cost_per_token": 2.2001e-07, + "input_dbu_cost_per_token": 3.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 262144, + "max_output_tokens": 25000, + "max_tokens": 25000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.20003e-06, + "output_dbu_cost_per_token": 3.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/databricks-qwen3-next-80b-a3b-instruct": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "databricks/databricks-qwen3-embedding-0-6b": { + "cache_creation_input_token_cost": 2.002e-08, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 2.002e-08, + "input_dbu_cost_per_token": 2.86e-07, + "litellm_provider": "databricks", + "max_input_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -31227,7 +31906,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31259,7 +31938,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31292,7 +31971,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31325,7 +32004,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31360,7 +32039,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31427,7 +32106,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -52723,7 +53402,7 @@ "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-07-23", "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -52756,7 +53435,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, 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 311ba7aebc0..0f8084643ea 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 @@ -4630,6 +4630,28 @@ def test_generic_cost_per_token_grok_46_long_context(_local_model_cost_map): assert completion_cost == pytest.approx(1_000 * 1.2e-05) +@pytest.mark.parametrize( + ("model", "provider", "image_token_rate"), + [ + ("gpt-realtime-2.1", "openai", 5e-06), + ("gpt-realtime-2.1-mini", "openai", 8e-07), + ("azure/gpt-realtime-2.1", "azure", 5e-06), + ("azure/gpt-realtime-2.1-mini", "azure", 8e-07), + ], +) +def test_realtime_image_tokens_priced_per_token(model, provider, image_token_rate, _local_model_cost_map): + """Realtime image input is billed per 1M image tokens, not per image.""" + usage = Usage( + prompt_tokens=1_100, + completion_tokens=0, + total_tokens=1_100, + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=100, image_tokens=1_000), + ) + prompt_cost, _ = generic_cost_per_token(model=model, usage=usage, custom_llm_provider=provider) + text_rate = litellm.model_cost[model]["input_cost_per_token"] + assert prompt_cost == pytest.approx(100 * text_rate + 1_000 * image_token_rate) + + @pytest.mark.parametrize( ("response_quality", "requested_quality", "expected_cost"), [ 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 e72642f7a04..0b251be5408 100644 --- a/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py +++ b/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py @@ -18,6 +18,10 @@ NEW_MODELS: Final = ( "databricks/databricks-claude-opus-5", "databricks/databricks-claude-sonnet-5", "databricks/databricks-claude-fable-5", + "databricks/databricks-claude-fable-5-1", + "databricks/databricks-gpt-5-6-sol", + "databricks/databricks-gpt-5-6-terra", + "databricks/databricks-gpt-5-6-luna", ) DOLLARS_PER_DBU: Final = Decimal("0.070") @@ -28,6 +32,7 @@ PRICE_FIELDS: Final = ( "cache_read_input_token_cost", ) PUBLISHED_DBU_PER_MILLION: Final = { + "databricks/databricks-claude-fable-5-1": ("142.858", "714.286", "178.572", "3.572"), "databricks/databricks-claude-fable-5": ("142.858", "714.286", "178.572", "14.286"), "databricks/databricks-claude-opus-5": ("71.429", "357.143", "89.286", "7.143"), "databricks/databricks-claude-opus-4-8": ("71.429", "357.143", "89.286", "7.143"), @@ -52,9 +57,17 @@ PUBLISHED_DBU_PER_MILLION: Final = { "databricks/databricks-gpt-5-2": ("25.000", "200.000", "25.000", "2.500"), "databricks/databricks-gpt-5-2-codex": ("25.000", "200.000", "25.000", "2.500"), "databricks/databricks-gpt-5-3-codex": ("25.000", "200.000", "25.000", "2.500"), + "databricks/databricks-gpt-5-6-sol": ("57.143", "285.714", "71.429", "5.714"), + "databricks/databricks-gpt-5-6-terra": ("35.714", "214.286", "44.643", "3.571"), + "databricks/databricks-gpt-5-6-luna": ("14.286", "85.714", "17.857", "1.429"), + "databricks/databricks-gpt-5-5": ("71.429", "428.571", "71.429", "7.143"), + "databricks/databricks-gpt-5-5-pro": ("428.571", "2571.429", "428.571", "428.571"), "databricks/databricks-gpt-5-4": ("35.714", "214.286", "35.714", "3.571"), "databricks/databricks-gpt-5-4-mini": ("10.714", "64.286", "10.714", "1.071"), "databricks/databricks-gpt-5-4-nano": ("2.857", "17.857", "2.857", "0.286"), + "databricks/databricks-gemini-3-6-flash": ("26.786", "133.929", "26.786", "2.679"), + "databricks/databricks-gemini-3-5-flash": ("26.786", "160.714", "26.786", "2.679"), + "databricks/databricks-gemini-3-5-flash-lite": ("5.357", "44.643", "5.357", "0.536"), "databricks/databricks-gemini-3-1-pro": ("35.714", "214.286", "35.714", "3.571"), "databricks/databricks-gemini-3-pro": ("35.714", "214.286", "35.714", "3.571"), "databricks/databricks-gemini-3-flash": ("8.929", "53.571", "8.929", "0.893"), @@ -65,6 +78,13 @@ PUBLISHED_DBU_PER_MILLION: Final = { "databricks/databricks-deepseek-v4-flash-0731": ("2.000", "4.000", "2.000", "0.400"), "databricks/databricks-deepseek-v4-pro-0813": ("18.857", "56.571", "18.857", "1.886"), "databricks/databricks-glm-5-2": ("20.000", "62.857", "20.000", "3.714"), + "databricks/databricks-glm-5-3": ("20.000", "62.857", "20.000", "3.714"), + "databricks/databricks-glm-5-3-flash": ("2.143", "7.143", "2.143", "0.429"), + "databricks/databricks-inkling": ("14.286", "57.857", "14.286", "2.429"), + "databricks/databricks-grok-4-6": ("35.714", "107.143", "35.714", "8.929"), + "databricks/databricks-qwen35-122b-a10b": ("3.143", "31.429", "3.143", "3.143"), + "databricks/databricks-qwen3-next-80b-a3b-instruct": ("2.143", "17.143", "2.143", "2.143"), + "databricks/databricks-qwen3-embedding-0-6b": ("0.286", "0", "0.286", "0.286"), } PROMOTIONAL_DISCOUNT: Final = 0.80 PROMOTION_EXPIRES: Final = "2027-01-31" @@ -73,6 +93,10 @@ ENTRIES_STORING_PROMOTIONAL_RATE: Final = ( "databricks/databricks-gemini-2-5-flash", ) ENTRIES_STORING_LIST_RATE_DESPITE_PROMOTION: Final = ( + "databricks/databricks-gemini-3-6-flash", + "databricks/databricks-gemini-3-5-flash", + "databricks/databricks-gemini-3-5-flash-lite", + "databricks/databricks-grok-4-6", "databricks/databricks-gemini-3-1-pro", "databricks/databricks-gemini-3-pro", "databricks/databricks-gemini-3-flash", From c707f2fe5d771c240f03ef18882229773b3db90d Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 14:32:11 +0000 Subject: [PATCH 18/23] fix(model_prices): databricks gpt-5-3-codex is served via the Responses API Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 2 +- model_prices_and_context_window.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7304ca04eb5..01bb7d434f5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -18089,7 +18089,7 @@ "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", + "mode": "responses", "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", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7304ca04eb5..01bb7d434f5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -18089,7 +18089,7 @@ "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", + "mode": "responses", "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", From 0c29f510bcdaa9f6d3cfb007c7ebda00458676ff Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 15:03:29 +0000 Subject: [PATCH 19/23] fix(registry): drop gpt-image-2 text output price, add openrouter minimax-m3 and qwen3.7-plus Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 39 +++++++++++++++++-- model_prices_and_context_window.json | 39 +++++++++++++++++-- .../test_gpt_image_cost_calculator.py | 19 ++------- tests/test_litellm/test_utils.py | 4 +- 4 files changed, 76 insertions(+), 25 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 01bb7d434f5..1a92d78b053 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -8296,7 +8296,6 @@ "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 1e-05, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -8312,7 +8311,6 @@ "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 1e-05, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -29225,7 +29223,6 @@ "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ @@ -29240,7 +29237,6 @@ "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ @@ -60797,5 +60793,40 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true + }, + "openrouter/minimax/minimax-m3": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6e-08, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.7-plus": { + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 1.28e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.7-plus", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6.4e-08, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 4e-07 } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 01bb7d434f5..1a92d78b053 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8296,7 +8296,6 @@ "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 1e-05, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -8312,7 +8311,6 @@ "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 1e-05, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -29225,7 +29223,6 @@ "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ @@ -29240,7 +29237,6 @@ "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ @@ -60797,5 +60793,40 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true + }, + "openrouter/minimax/minimax-m3": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6e-08, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.7-plus": { + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 1.28e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.7-plus", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6.4e-08, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 4e-07 } } diff --git a/tests/test_litellm/test_gpt_image_cost_calculator.py b/tests/test_litellm/test_gpt_image_cost_calculator.py index d3ec0673fe3..86a721f8743 100644 --- a/tests/test_litellm/test_gpt_image_cost_calculator.py +++ b/tests/test_litellm/test_gpt_image_cost_calculator.py @@ -172,8 +172,7 @@ class TestGPTImageCostCalculator: image_tokens=500, ), completion_tokens_details=CompletionTokensDetailsWrapper( - text_tokens=1000, - image_tokens=4000, + image_tokens=5000, ), ) @@ -189,12 +188,7 @@ class TestGPTImageCostCalculator: custom_llm_provider="openai", ) - # GPT Image 2 pricing: - # Text input: 100 * $5/1M = 0.0005 - # Image input: 500 * $8/1M = 0.004 - # Text output: 1000 * $10/1M = 0.01 - # Image output: 4000 * $30/1M = 0.12 - expected_cost = 0.0005 + 0.004 + 0.01 + 0.12 + expected_cost = 100 * 5e-6 + 500 * 8e-6 + 5000 * 3e-5 assert abs(cost - expected_cost) < 1e-6, f"Expected {expected_cost}, got {cost}" @@ -429,10 +423,7 @@ class TestGPTImage2OutputImageTokensNoBreakdown: f"are likely being priced at the text output_cost_per_token rate." ) - def test_gpt_image_2_chat_usage_without_breakdown_is_costed_not_zero(self): - """A chat ``Usage`` with ``completion_tokens_details=None`` must still be - costed via ``generic_cost_per_token`` (output at the text rate) rather than - erroring or silently returning 0.0.""" + def test_gpt_image_2_chat_usage_without_breakdown_uses_image_rate(self): from litellm.llms.openai.image_generation.cost_calculator import ( cost_calculator, ) @@ -460,9 +451,7 @@ class TestGPTImage2OutputImageTokensNoBreakdown: custom_llm_provider="openai", ) - # No output breakdown -> output priced at the text rate (output_cost_per_token): - # text in 100*$5/1M + image in 500*$8/1M + output 5000*$10/1M - expected_cost = 100 * 5e-6 + 500 * 8e-6 + 5000 * 1e-5 + expected_cost = 100 * 5e-6 + 500 * 8e-6 + 5000 * 3e-5 assert abs(cost - expected_cost) < 1e-6, f"Expected {expected_cost}, got {cost}" diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 38a09415ed0..a170bbee8e2 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -430,7 +430,7 @@ def test_gpt_image_2_provider_and_model_info(local_model_cost_map): assert model_info["mode"] == "image_generation" assert model_info["input_cost_per_token"] == 5e-06 assert model_info["input_cost_per_image_token"] == 8e-06 - assert model_info["output_cost_per_token"] == 1e-05 + assert model_info["output_cost_per_token"] == 0 assert model_info["output_cost_per_image_token"] == 3e-05 assert ( "/v1/images/generations" @@ -472,7 +472,7 @@ def test_azure_gpt_image_2_model_info(local_model_cost_map): assert model_info["mode"] == "image_generation" assert model_info["input_cost_per_token"] == 5e-06 assert model_info["input_cost_per_image_token"] == 8e-06 - assert model_info["output_cost_per_token"] == 1e-05 + assert model_info["output_cost_per_token"] == 0 assert model_info["output_cost_per_image_token"] == 3e-05 From 7b96a11e5f5605c3bd21b5aa7e9b9161530b0b96 Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 19:19:08 +0000 Subject: [PATCH 20/23] feat(registry): add OpenRouter catalog gaps, Fireworks DeepSeek V4 Flash Vision, Together MiniMax M2.7 and Qwen2.5 7B Turbo pricing Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 2184 ++++++++++++++++- model_prices_and_context_window.json | 2184 ++++++++++++++++- model_prices_and_context_window.schema.json | 20 + 3 files changed, 4386 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1a92d78b053..aa4f9b87377 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -42472,7 +42472,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 3e-07, + "max_input_tokens": 32768, + "max_tokens": 32768, + "source": "https://www.together.ai/pricing" }, "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "deprecation_date": "2026-07-10", @@ -42894,6 +42899,16 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/MiniMaxAI/MiniMax-M2.7": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 196608, + "max_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.together.ai/pricing" + }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", @@ -56337,6 +56352,19 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -56374,6 +56402,19 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, @@ -60828,5 +60869,2146 @@ "cache_read_input_token_cost": 6.4e-08, "supports_prompt_caching": true, "cache_creation_input_token_cost": 4e-07 + }, + "openrouter/openai/gpt-6-astra": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-6-astra", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-flash": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.7e-07, + "cache_read_input_token_cost": 1.6e-08, + "cache_creation_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.3-flash": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 2.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.3-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v4-flash-vision-exp": { + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 6.6e-07, + "cache_read_input_token_cost": 7e-09, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.3": { + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-27b": { + "input_cost_per_token": 4.2e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 8.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-27b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-2.4t-a95b": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3.5-lightning:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3.8-max": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v4-flash-0731": { + "input_cost_per_token": 6.5e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.7-flash": { + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, + "cache_read_input_token_cost": 6e-09, + "cache_creation_input_token_cost": 3.8e-08, + "input_cost_per_token_above_256k_tokens": 2e-07, + "output_cost_per_token_above_256k_tokens": 8e-07, + "cache_read_input_token_cost_above_256k_tokens": 4e-08, + "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.7-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-s-2.1": { + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 9e-09, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-s-2.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-s-2.1:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-s-2.1:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/moonshotai/kimi-k3": { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-xs-2.1": { + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-xs-2.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-xs-2.1:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-xs-2.1:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/google/gemini-3.1-flash-lite-image": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "output_cost_per_image_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-flash-lite-image", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-3.1-flash-image": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_image_token": 6e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-flash-image", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-3-pro-image": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 2e-06, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3-pro-image", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.2": { + "input_cost_per_token": 9.66e-07, + "output_cost_per_token": 3.036e-06, + "cache_read_input_token_cost": 1.932e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.2:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 230400, + "max_tokens": 230400, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.2:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/moonshotai/kimi-k2.7-code": { + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 3.4e-06, + "cache_read_input_token_cost": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2.7-code", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3.5-content-safety": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/nvidia/nemotron-3.5-content-safety:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_vision": true + }, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { + "input_cost_per_token": 6.25e-07, + "output_cost_per_token": 3.125e-06, + "cache_read_input_token_cost": 1.875e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-m3:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m3:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.7-max": { + "input_cost_per_token": 1.475e-06, + "output_cost_per_token": 4.425e-06, + "cache_read_input_token_cost": 2.95e-07, + "cache_creation_input_token_cost": 1.84375e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.7-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-medium-3-5": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-medium-3-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_audio_input": true + }, + "openrouter/qwen/qwen3.5-plus-20260420": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.8e-06, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_token_above_256k_tokens": 3.75e-07, + "output_cost_per_token_above_256k_tokens": 2.25e-06, + "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.5-plus-20260420", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.6-flash": { + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 1.125e-06, + "cache_creation_input_token_cost": 2.34375e-07, + "input_cost_per_token_above_256k_tokens": 7.5e-07, + "output_cost_per_token_above_256k_tokens": 3e-06, + "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-35b-a3b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.6-max-preview": { + "input_cost_per_token": 1.027e-06, + "output_cost_per_token": 6.162e-06, + "cache_creation_input_token_cost": 1.28375e-06, + "input_cost_per_token_above_128k_tokens": 1.58e-06, + "output_cost_per_token_above_128k_tokens": 9.48e-06, + "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-max-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": 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, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-27b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens": 0.00027, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.5-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/deepseek/deepseek-v4-flash": { + "input_cost_per_token": 8.778e-08, + "output_cost_per_token": 1.7556e-07, + "cache_read_input_token_cost": 1.7556e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v4-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/moonshotai/kimi-k2.6": { + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 1.6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2.6", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 7e-08, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-4-26b-a4b-it:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-4-31b-it": { + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.4e-07, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-31b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemma-4-31b-it:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-31b-it:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/z-ai/glm-5v-turbo": { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5v-turbo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/minimax/minimax-m2.7": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2.7", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/minimax/minimax-m2.7:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 196608, + "max_output_tokens": 176947, + "max_tokens": 176947, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2.7:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/mistralai/mistral-small-2603": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-small-2603", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5-turbo": { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5-turbo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3-super-120b-a12b": { + "input_cost_per_token": 8.5e-08, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3.5-9b": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.5-9b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5.4-pro": { + "input_cost_per_token": 3e-05, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens": 0.00027, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/google/gemini-3.1-flash-image-preview": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_image_token": 6e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-flash-image-preview", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-3.1-pro-preview-customtools": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-pro-preview-customtools", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-max-thinking": { + "input_cost_per_token": 7.8e-07, + "output_cost_per_token": 3.9e-06, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-max-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-coder-next": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-coder-next", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/minimax/minimax-m2-her": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2-her", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-audio": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "input_cost_per_audio_token": 3.2e-05, + "output_cost_per_audio_token": 6.4e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-audio", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_audio_input": true + }, + "openrouter/openai/gpt-audio-mini": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.4e-06, + "input_cost_per_audio_token": 6e-07, + "output_cost_per_audio_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-audio-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_audio_input": true + }, + "openrouter/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-4.6v": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 5.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.6v", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3-pro-image-preview": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 2e-06, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3-pro-image-preview", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.1-codex": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.1-codex", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.1-codex-mini": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.1-codex-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/moonshotai/kimi-k2-thinking": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/voxtral-small-24b-2507": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_audio_token": 0.0001, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/voxtral-small-24b-2507", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.75e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-oss-safeguard-20b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.04e-07, + "output_cost_per_token": 4.16e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-32b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-8b-thinking": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 2.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-8b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-8b-instruct": { + "input_cost_per_token": 1.17e-07, + "output_cost_per_token": 4.55e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-8b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-flash-image": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 8.33333333333333e-08, + "input_cost_per_audio_token": 1e-06, + "output_cost_per_image_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-flash-image", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 2.1e-07, + "output_cost_per_token": 1.9e-06, + "cache_read_input_token_cost": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-max": { + "input_cost_per_token": 7.8e-07, + "output_cost_per_token": 3.9e-06, + "cache_read_input_token_cost": 1.56e-07, + "cache_creation_input_token_cost": 9.75e-07, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, + "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v3.1-terminus": { + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1.35e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v3.1-terminus", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-coder-flash": { + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 9.75e-07, + "cache_read_input_token_cost": 3.9e-08, + "cache_creation_input_token_cost": 2.4375e-07, + "input_cost_per_token_above_128k_tokens": 5.2e-07, + "output_cost_per_token_above_128k_tokens": 2.6e-06, + "cache_read_input_token_cost_above_128k_tokens": 1.04e-07, + "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-coder-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.1e-06, + "cache_read_input_token_cost": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen-plus-2025-07-28": { + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 7.8e-07, + "input_cost_per_token_above_256k_tokens": 7.8e-07, + "output_cost_per_token_above_256k_tokens": 2.34e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-plus-2025-07-28", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/moonshotai/kimi-k2-0905": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2-0905", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 81920, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-thinking-2507", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/mistralai/mistral-medium-3.1": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-medium-3.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-4.5v": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 1.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.5v", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/codestral-2508": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/codestral-2508", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { + "input_cost_per_token": 4.815e-08, + "output_cost_per_token": 1.9305e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/z-ai/glm-4.5": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-4.5-air": { + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 8.5e-07, + "cache_read_input_token_cost": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.5-air", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/moonshotai/kimi-k2": { + "input_cost_per_token": 5.7e-07, + "output_cost_per_token": 2.3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 100352, + "max_tokens": 100352, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-m1": { + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/openai/o3-pro": { + "input_cost_per_token": 2e-05, + "output_cost_per_token": 8e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o3-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/google/gemini-2.5-pro-preview": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-pro-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-medium-3": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-medium-3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-2.5-pro-preview-05-06": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-guard-4-12b": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-guard-4-12b", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-30b-a3b": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-30b-a3b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-8b": { + "input_cost_per_token": 1.17e-07, + "output_cost_per_token": 4.55e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-8b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-14b": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-14b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-32b": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-32b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-235b-a22b": { + "input_cost_per_token": 4.55e-07, + "output_cost_per_token": 1.82e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-235b-a22b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/o4-mini-high": { + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o4-mini-high", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-4-maverick": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6.96e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-4-maverick", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/meta-llama/llama-4-scout": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-4-scout", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/o1-pro": { + "input_cost_per_token": 0.00015, + "output_cost_per_token": 0.0006, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o1-pro", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/google/gemma-3-4b-it": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-3-4b-it", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-3-12b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-3-27b-it": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 4.5e-07, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-3-27b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-saba": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-saba", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen2.5-vl-72b-instruct": { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen-plus": { + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 7.8e-07, + "cache_read_input_token_cost": 5.2e-08, + "cache_creation_input_token_cost": 3.25e-07, + "input_cost_per_token_above_256k_tokens": 7.8e-07, + "output_cost_per_token_above_256k_tokens": 2.34e-06, + "cache_read_input_token_cost_above_256k_tokens": 1.56e-07, + "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-plus", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-small-24b-instruct-2501": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 7372, + "max_tokens": 7372, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-01": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000192, + "max_output_tokens": 900172, + "max_tokens": 900172, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-01", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_vision": true + }, + "openrouter/meta-llama/llama-3.3-70b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4o-2024-11-20": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-2024-11-20", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-large-2407": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-large-2407", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen-2.5-7b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-2.5-7b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2.7e-08, + "output_cost_per_token": 2.01e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 60000, + "max_output_tokens": 54000, + "max_tokens": 54000, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.2-1b-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_vision": false + }, + "openrouter/meta-llama/llama-3.2-3b-instruct": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 3.3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.2-3b-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen-2.5-72b-instruct": { + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4o-2024-08-06": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-2024-08-06", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-3.1-70b-instruct": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.1-70b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/meta-llama/llama-3.1-8b-instruct": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "cache_read_input_token_cost": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.1-8b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-nemo": { + "input_cost_per_token": 1.9e-08, + "output_cost_per_token": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-nemo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4o-mini-2024-07-18": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-mini-2024-07-18", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemma-2-27b-it": { + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-2-27b-it", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4-turbo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4-turbo-preview": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 4095, + "max_output_tokens": 3685, + "max_tokens": 3685, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-3.5-turbo-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1a92d78b053..aa4f9b87377 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -42472,7 +42472,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 3e-07, + "max_input_tokens": 32768, + "max_tokens": 32768, + "source": "https://www.together.ai/pricing" }, "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "deprecation_date": "2026-07-10", @@ -42894,6 +42899,16 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/MiniMaxAI/MiniMax-M2.7": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 196608, + "max_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.together.ai/pricing" + }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", @@ -56337,6 +56352,19 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -56374,6 +56402,19 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, @@ -60828,5 +60869,2146 @@ "cache_read_input_token_cost": 6.4e-08, "supports_prompt_caching": true, "cache_creation_input_token_cost": 4e-07 + }, + "openrouter/openai/gpt-6-astra": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-6-astra", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-flash": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.7e-07, + "cache_read_input_token_cost": 1.6e-08, + "cache_creation_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.3-flash": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 2.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.3-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v4-flash-vision-exp": { + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 6.6e-07, + "cache_read_input_token_cost": 7e-09, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.3": { + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-27b": { + "input_cost_per_token": 4.2e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 8.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-27b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-2.4t-a95b": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3.5-lightning:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3.8-max": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v4-flash-0731": { + "input_cost_per_token": 6.5e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.7-flash": { + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, + "cache_read_input_token_cost": 6e-09, + "cache_creation_input_token_cost": 3.8e-08, + "input_cost_per_token_above_256k_tokens": 2e-07, + "output_cost_per_token_above_256k_tokens": 8e-07, + "cache_read_input_token_cost_above_256k_tokens": 4e-08, + "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.7-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-s-2.1": { + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 9e-09, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-s-2.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-s-2.1:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-s-2.1:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/moonshotai/kimi-k3": { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-xs-2.1": { + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-xs-2.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/poolside/laguna-xs-2.1:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/poolside/laguna-xs-2.1:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/google/gemini-3.1-flash-lite-image": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "output_cost_per_image_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-flash-lite-image", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-3.1-flash-image": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_image_token": 6e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-flash-image", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-3-pro-image": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 2e-06, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3-pro-image", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.2": { + "input_cost_per_token": 9.66e-07, + "output_cost_per_token": 3.036e-06, + "cache_read_input_token_cost": 1.932e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5.2:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 230400, + "max_tokens": 230400, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5.2:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/moonshotai/kimi-k2.7-code": { + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 3.4e-06, + "cache_read_input_token_cost": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2.7-code", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3.5-content-safety": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/nvidia/nemotron-3.5-content-safety:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_vision": true + }, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { + "input_cost_per_token": 6.25e-07, + "output_cost_per_token": 3.125e-06, + "cache_read_input_token_cost": 1.875e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-m3:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m3:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.7-max": { + "input_cost_per_token": 1.475e-06, + "output_cost_per_token": 4.425e-06, + "cache_read_input_token_cost": 2.95e-07, + "cache_creation_input_token_cost": 1.84375e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.7-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-medium-3-5": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-medium-3-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_audio_input": true + }, + "openrouter/qwen/qwen3.5-plus-20260420": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.8e-06, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_token_above_256k_tokens": 3.75e-07, + "output_cost_per_token_above_256k_tokens": 2.25e-06, + "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.5-plus-20260420", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.6-flash": { + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 1.125e-06, + "cache_creation_input_token_cost": 2.34375e-07, + "input_cost_per_token_above_256k_tokens": 7.5e-07, + "output_cost_per_token_above_256k_tokens": 3e-06, + "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-35b-a3b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.6-max-preview": { + "input_cost_per_token": 1.027e-06, + "output_cost_per_token": 6.162e-06, + "cache_creation_input_token_cost": 1.28375e-06, + "input_cost_per_token_above_128k_tokens": 1.58e-06, + "output_cost_per_token_above_128k_tokens": 9.48e-06, + "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-max-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": 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, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.6-27b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens": 0.00027, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.5-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/deepseek/deepseek-v4-flash": { + "input_cost_per_token": 8.778e-08, + "output_cost_per_token": 1.7556e-07, + "cache_read_input_token_cost": 1.7556e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v4-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/moonshotai/kimi-k2.6": { + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 1.6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2.6", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 7e-08, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-4-26b-a4b-it:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-4-31b-it": { + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.4e-07, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-31b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemma-4-31b-it:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-4-31b-it:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/z-ai/glm-5v-turbo": { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5v-turbo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/minimax/minimax-m2.7": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2.7", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/minimax/minimax-m2.7:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 196608, + "max_output_tokens": 176947, + "max_tokens": 176947, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2.7:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/mistralai/mistral-small-2603": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-small-2603", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-5-turbo": { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-5-turbo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/nvidia/nemotron-3-super-120b-a12b": { + "input_cost_per_token": 8.5e-08, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3.5-9b": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.5-9b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5.4-pro": { + "input_cost_per_token": 3e-05, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens": 0.00027, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.4-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/google/gemini-3.1-flash-image-preview": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_image_token": 6e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-flash-image-preview", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-3.1-pro-preview-customtools": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3.1-pro-preview-customtools", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-max-thinking": { + "input_cost_per_token": 7.8e-07, + "output_cost_per_token": 3.9e-06, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-max-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-coder-next": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-coder-next", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/minimax/minimax-m2-her": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2-her", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-audio": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "input_cost_per_audio_token": 3.2e-05, + "output_cost_per_audio_token": 6.4e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-audio", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_audio_input": true + }, + "openrouter/openai/gpt-audio-mini": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.4e-06, + "input_cost_per_audio_token": 6e-07, + "output_cost_per_audio_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-audio-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_audio_input": true + }, + "openrouter/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-4.6v": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 5.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.6v", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-3-pro-image-preview": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 2e-06, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-3-pro-image-preview", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.1-codex": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.1-codex", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-5.1-codex-mini": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5.1-codex-mini", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/moonshotai/kimi-k2-thinking": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/voxtral-small-24b-2507": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_audio_token": 0.0001, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/voxtral-small-24b-2507", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/openai/gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.75e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-oss-safeguard-20b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.04e-07, + "output_cost_per_token": 4.16e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-32b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-8b-thinking": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 2.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-8b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-8b-instruct": { + "input_cost_per_token": 1.17e-07, + "output_cost_per_token": 4.55e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-8b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-flash-image": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 8.33333333333333e-08, + "input_cost_per_audio_token": 1e-06, + "output_cost_per_image_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-flash-image", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-5-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 2.1e-07, + "output_cost_per_token": 1.9e-06, + "cache_read_input_token_cost": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-max": { + "input_cost_per_token": 7.8e-07, + "output_cost_per_token": 3.9e-06, + "cache_read_input_token_cost": 1.56e-07, + "cache_creation_input_token_cost": 9.75e-07, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, + "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v3.1-terminus": { + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1.35e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-v3.1-terminus", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-coder-flash": { + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 9.75e-07, + "cache_read_input_token_cost": 3.9e-08, + "cache_creation_input_token_cost": 2.4375e-07, + "input_cost_per_token_above_128k_tokens": 5.2e-07, + "output_cost_per_token_above_128k_tokens": 2.6e-06, + "cache_read_input_token_cost_above_128k_tokens": 1.04e-07, + "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-coder-flash", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.1e-06, + "cache_read_input_token_cost": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen-plus-2025-07-28": { + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 7.8e-07, + "input_cost_per_token_above_256k_tokens": 7.8e-07, + "output_cost_per_token_above_256k_tokens": 2.34e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-plus-2025-07-28", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/moonshotai/kimi-k2-0905": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2-0905", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 81920, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-thinking-2507", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/mistralai/mistral-medium-3.1": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-medium-3.1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-4.5v": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 1.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.5v", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/codestral-2508": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/codestral-2508", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { + "input_cost_per_token": 4.815e-08, + "output_cost_per_token": 1.9305e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/z-ai/glm-4.5": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/z-ai/glm-4.5-air": { + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 8.5e-07, + "cache_read_input_token_cost": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/z-ai/glm-4.5-air", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/moonshotai/kimi-k2": { + "input_cost_per_token": 5.7e-07, + "output_cost_per_token": 2.3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 100352, + "max_tokens": 100352, + "mode": "chat", + "source": "https://openrouter.ai/moonshotai/kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-m1": { + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m1", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/openai/o3-pro": { + "input_cost_per_token": 2e-05, + "output_cost_per_token": 8e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o3-pro", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/google/gemini-2.5-pro-preview": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-pro-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-medium-3": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-medium-3", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-2.5-pro-preview-05-06": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-guard-4-12b": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-guard-4-12b", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3-30b-a3b": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-30b-a3b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-8b": { + "input_cost_per_token": 1.17e-07, + "output_cost_per_token": 4.55e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-8b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-14b": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-14b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-32b": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-32b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen3-235b-a22b": { + "input_cost_per_token": 4.55e-07, + "output_cost_per_token": 1.82e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3-235b-a22b", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/o4-mini-high": { + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o4-mini-high", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-4-maverick": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6.96e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-4-maverick", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/meta-llama/llama-4-scout": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-4-scout", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/o1-pro": { + "input_cost_per_token": 0.00015, + "output_cost_per_token": 0.0006, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/openai/o1-pro", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true + }, + "openrouter/google/gemma-3-4b-it": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-3-4b-it", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-3-12b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/google/gemma-3-27b-it": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 4.5e-07, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-3-27b-it", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-saba": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-saba", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen2.5-vl-72b-instruct": { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen-plus": { + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 7.8e-07, + "cache_read_input_token_cost": 5.2e-08, + "cache_creation_input_token_cost": 3.25e-07, + "input_cost_per_token_above_256k_tokens": 7.8e-07, + "output_cost_per_token_above_256k_tokens": 2.34e-06, + "cache_read_input_token_cost_above_256k_tokens": 1.56e-07, + "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-plus", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-small-24b-instruct-2501": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 7372, + "max_tokens": 7372, + "mode": "chat", + "source": "https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-01": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000192, + "max_output_tokens": 900172, + "max_tokens": 900172, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-01", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_vision": true + }, + "openrouter/meta-llama/llama-3.3-70b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4o-2024-11-20": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-2024-11-20", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-large-2407": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-large-2407", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen-2.5-7b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-2.5-7b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2.7e-08, + "output_cost_per_token": 2.01e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 60000, + "max_output_tokens": 54000, + "max_tokens": 54000, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.2-1b-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_vision": false + }, + "openrouter/meta-llama/llama-3.2-3b-instruct": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 3.3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.2-3b-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/qwen/qwen-2.5-72b-instruct": { + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4o-2024-08-06": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-2024-08-06", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-3.1-70b-instruct": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.1-70b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/meta-llama/llama-3.1-8b-instruct": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "cache_read_input_token_cost": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/meta-llama/llama-3.1-8b-instruct", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true + }, + "openrouter/mistralai/mistral-nemo": { + "input_cost_per_token": 1.9e-08, + "output_cost_per_token": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/mistralai/mistral-nemo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4o-mini-2024-07-18": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4o-mini-2024-07-18", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemma-2-27b-it": { + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/google/gemma-2-27b-it", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4-turbo", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4-turbo-preview": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 4095, + "max_output_tokens": 3685, + "max_tokens": 3685, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-3.5-turbo-instruct", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false } } diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 9e370e5406a..a51149bf958 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -79,6 +79,11 @@ "minimum": 0, "description": "USD per token written to the provider's prompt cache." }, + "cache_creation_input_token_cost_above_128k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_creation_input_token_cost_above_1hr": { "type": "number", "minimum": 0, @@ -94,6 +99,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_creation_input_token_cost_above_256k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_creation_input_token_cost_above_272k_tokens": { "type": "number", "minimum": 0, @@ -128,6 +138,11 @@ "minimum": 0, "description": "USD per prompt token served from the provider's prompt cache." }, + "cache_read_input_token_cost_above_128k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_read_input_token_cost_above_200k_tokens": { "type": "number", "minimum": 0, @@ -138,6 +153,11 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, + "cache_read_input_token_cost_above_256k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_read_input_token_cost_above_272k_tokens": { "type": "number", "minimum": 0, From 1f0611a8b90a57df101200a981a1029d79017b06 Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 19:25:10 +0000 Subject: [PATCH 21/23] fix(registry): drop Together MiniMax M2.7 and revert Qwen2.5 7B Turbo pricing, both non-serverless Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../model_prices_and_context_window_backup.json | 17 +---------------- model_prices_and_context_window.json | 17 +---------------- 2 files changed, 2 insertions(+), 32 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index aa4f9b87377..476fe4143c1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -42472,12 +42472,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "max_input_tokens": 32768, - "max_tokens": 32768, - "source": "https://www.together.ai/pricing" + "supports_tool_choice": true }, "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "deprecation_date": "2026-07-10", @@ -42899,16 +42894,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "together_ai/MiniMaxAI/MiniMax-M2.7": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://www.together.ai/pricing" - }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index aa4f9b87377..476fe4143c1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -42472,12 +42472,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "max_input_tokens": 32768, - "max_tokens": 32768, - "source": "https://www.together.ai/pricing" + "supports_tool_choice": true }, "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "deprecation_date": "2026-07-10", @@ -42899,16 +42894,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "together_ai/MiniMaxAI/MiniMax-M2.7": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://www.together.ai/pricing" - }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", From f5157a63eb030b8130be567b03c49deac226cd70 Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 19:56:30 +0000 Subject: [PATCH 22/23] test: allow 128k and 256k tiered cache fields in registry schema test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- tests/test_litellm/test_utils.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 580d8dfcc09..14907e17b1b 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -906,7 +906,9 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_audio_token_cost": {"type": "number"}, "cache_creation_input_token_cost": {"type": "number"}, "cache_creation_input_token_cost_above_1hr": {"type": "number"}, + "cache_creation_input_token_cost_above_128k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"}, + "cache_creation_input_token_cost_above_256k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_272k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_272k_tokens_flex": { "type": "number" @@ -917,7 +919,9 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost_flex": {"type": "number"}, "cache_creation_input_token_cost_priority": {"type": "number"}, "cache_read_input_token_cost": {"type": "number"}, + "cache_read_input_token_cost_above_128k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_200k_tokens": {"type": "number"}, + "cache_read_input_token_cost_above_256k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_272k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_272k_tokens_flex": { "type": "number" From 50d6b26a86ea3c374bdd872a644ccdc5e61ceb47 Mon Sep 17 00:00:00 2001 From: mateo Date: Fri, 4 Sep 2026 20:10:58 +0000 Subject: [PATCH 23/23] fix(registry): mark baseten GLM-5.3 as vision-capable per Baseten vision docs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 6 ++++-- model_prices_and_context_window.json | 6 ++++-- tests/test_litellm/test_baseten_glm_5_3_model_metadata.py | 3 ++- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 476fe4143c1..7f5038e3073 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -60810,7 +60810,8 @@ "output_cost_per_token": 4.4e-06, "source": "https://www.baseten.co/pricing/", "supported_modalities": [ - "text" + "text", + "image" ], "supported_output_modalities": [ "text" @@ -60818,7 +60819,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "openrouter/minimax/minimax-m3": { "input_cost_per_token": 3e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 476fe4143c1..7f5038e3073 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -60810,7 +60810,8 @@ "output_cost_per_token": 4.4e-06, "source": "https://www.baseten.co/pricing/", "supported_modalities": [ - "text" + "text", + "image" ], "supported_output_modalities": [ "text" @@ -60818,7 +60819,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "openrouter/minimax/minimax-m3": { "input_cost_per_token": 3e-07, diff --git a/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py b/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py index 98a8cf026ec..1dc17067d9f 100644 --- a/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py +++ b/tests/test_litellm/test_baseten_glm_5_3_model_metadata.py @@ -54,7 +54,8 @@ def test_baseten_glm_5_3_specs(): assert info["supports_prompt_caching"] is True assert info["supports_response_schema"] is True assert info["supports_tool_choice"] is True - assert info["supported_modalities"] == ["text"] + assert info["supports_vision"] is True + assert info["supported_modalities"] == ["text", "image"] assert info["supported_output_modalities"] == ["text"] routed_model, provider, _, _ = get_llm_provider(model=MODEL)