From 4695ad1deb1a30c8db5345329711b56aa526ba4f Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Wed, 4 Nov 2026 23:49:00 +0000 Subject: [PATCH] fix(bedrock): price claude_platform calls from their own cost map rows (#48150) Backport of #48150 to lts/1.108.x. Cherry-picked from 560372456eff (main). --- litellm/llms/bedrock/cost_calculation.py | 14 +- ...odel_prices_and_context_window_backup.json | 1223 +++++++++++++++-- model_prices_and_context_window.json | 1223 +++++++++++++++-- .../llms/bedrock/test_cost_calculation.py | 41 + tests/unit/test_utils_get_model_info.py | 1 + 5 files changed, 2295 insertions(+), 207 deletions(-) create mode 100644 tests/unit/llms/bedrock/test_cost_calculation.py diff --git a/litellm/llms/bedrock/cost_calculation.py b/litellm/llms/bedrock/cost_calculation.py index 0a2e39ab972..1b45531dda4 100644 --- a/litellm/llms/bedrock/cost_calculation.py +++ b/litellm/llms/bedrock/cost_calculation.py @@ -3,9 +3,13 @@ Helper util for handling bedrock-specific cost calculation - e.g.: prompt caching """ -from typing import TYPE_CHECKING +from typing import TYPE_CHECKING, Final -from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token +import litellm +from litellm.litellm_core_utils.llm_cost_calc.utils import ( + generic_cost_per_token, + get_provider_specific_geo_multiplier, +) if TYPE_CHECKING: from litellm.types.utils import Usage @@ -17,9 +21,13 @@ def cost_per_token(model: str, usage: "Usage", service_tier: str | None = None) Follows the same logic as Anthropic's cost per token calculation. """ - return generic_cost_per_token( + model_info: Final = litellm.get_model_info(model=model, custom_llm_provider="bedrock") + prompt_cost, completion_cost = generic_cost_per_token( model=model, usage=usage, custom_llm_provider="bedrock", service_tier=service_tier, + model_info=model_info, ) + geo_multiplier: Final = get_provider_specific_geo_multiplier(model_info=model_info, usage=usage) + return prompt_cost * geo_multiplier, completion_cost * geo_multiplier diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 98fee42de3c..583b8cb2b8e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -8899,7 +8899,11 @@ "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8952,7 +8956,11 @@ "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -9644,7 +9652,11 @@ "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, "output_cost_per_token_priority": 2.2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -16419,7 +16431,10 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "provider_specific_entry": {"us":1.1,"fast":2}, + "provider_specific_entry": { + "us": 1.1, + "fast": 2 + }, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, @@ -28970,7 +28985,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -29085,7 +29104,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -29138,7 +29161,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { @@ -29189,7 +29216,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -29233,7 +29264,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { @@ -29329,7 +29364,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29391,7 +29430,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -29452,7 +29495,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29539,7 +29586,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, @@ -29594,7 +29645,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -29641,7 +29696,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -29829,7 +29888,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, + "search_free_requests": { + "count": 10000, + "period": "day", + "shared_group": "gemini-2.5-pro" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, @@ -29866,8 +29929,16 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29948,7 +30019,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30005,7 +30080,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { @@ -30029,8 +30108,16 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30113,7 +30200,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -30179,7 +30270,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30241,7 +30336,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30267,8 +30366,16 @@ "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30415,8 +30522,16 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30503,7 +30618,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30831,7 +30950,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -30876,7 +30999,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -30938,7 +31065,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -31088,7 +31219,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, @@ -31201,7 +31336,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "supports_reasoning": true }, @@ -31265,8 +31404,16 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "rpm": 1000.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -31343,7 +31490,11 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "rpm": 1000.0, - "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_context_cost_per_query": { + "search_context_size_low": 0.035, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.035 + }, "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", @@ -31417,7 +31568,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, "input_cost_per_audio_token_priority": 5.4e-07, @@ -31623,7 +31778,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, + "search_free_requests": { + "count": 10000, + "period": "day", + "shared_group": "gemini-2.5-pro" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -31721,7 +31880,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07, @@ -31784,7 +31947,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -31841,7 +32008,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -31905,7 +32076,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -31972,7 +32147,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32035,7 +32214,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32098,7 +32281,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32194,7 +32381,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -32258,7 +32449,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -32286,8 +32481,16 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -32402,7 +32605,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -32468,7 +32675,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32530,7 +32741,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32555,8 +32770,16 @@ "output_cost_per_token_flex": 1.875e-06, "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -41522,7 +41745,7 @@ "supports_xhigh_reasoning_effort": true }, "meta/muse-voice-transcribe-1.0": { - "input_cost_per_second": 0.00005, + "input_cost_per_second": 5e-05, "litellm_provider": "meta", "mode": "audio_transcription", "source": "https://dev.meta.ai/docs/speech-to-text", @@ -52343,7 +52566,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -52377,7 +52599,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, @@ -52410,7 +52631,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -52435,7 +52655,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, @@ -52530,7 +52749,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -52593,7 +52816,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -52655,7 +52882,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -61612,11 +61843,41 @@ "output_cost_per_second_480p": 0.096075, "output_cost_per_second_720p": 0.216, "output_cost_per_second_1080p": 0.5346, - "supported_modalities": ["text", "image", "video", "audio"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "854x480", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "480x854", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "volcengine/doubao-seedance-2-0-260128": { "litellm_provider": "volcengine", @@ -61627,11 +61888,41 @@ "output_cost_per_second_720p": 0.141942857, "output_cost_per_second_1080p": 0.354085714, "output_cost_per_second_4k": 0.722057143, - "supported_modalities": ["text", "image", "video", "audio"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "864x496", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "496x864", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "volcengine/doubao-seedance-2-0-fast-260128": { "litellm_provider": "volcengine", @@ -61640,11 +61931,41 @@ "output_cost_per_second": 0.114171429, "output_cost_per_second_480p": 0.053089714, "output_cost_per_second_720p": 0.114171429, - "supported_modalities": ["text", "image", "video", "audio"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "864x496", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "496x864", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "volcengine/doubao-seedance-2-0-mini-260615": { "litellm_provider": "volcengine", @@ -61653,11 +61974,39 @@ "output_cost_per_second": 0.070971429, "output_cost_per_second_480p": 0.033001714, "output_cost_per_second_720p": 0.070971429, - "supported_modalities": ["text", "image"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "864x496", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "496x864", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, @@ -63518,7 +63867,13 @@ { "name": "claude-adaptive-thinking", "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.6 or higher, in any id shape that contains claude--: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Turns on adaptive thinking for new versions and new families with no code change.", "model_info": { "supports_adaptive_thinking": true @@ -63527,7 +63882,13 @@ { "name": "claude-legacy-thinking", "pattern": "claude-[a-z]+-4[-._]6(?!\\d)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.6 exactly, in any id shape that contains claude--4-6 (dotted and underscored minors included, dated releases such as claude-sonnet-4-6-20260219 too). The 4.6 family is adaptive-thinking yet still accepts legacy thinking.type=enabled with budget_tokens, so the caller's hard budget cap is forwarded verbatim instead of being rewritten to an uncapped output_config.effort. The lookahead keeps two-digit minors such as 4-60 from matching. 4.7+ and 5+ majors reject the legacy shape and stay on the adaptive translation.", "model_info": { "supports_legacy_thinking": true @@ -63544,7 +63905,13 @@ { "name": "claude-mid-conversation-system", "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.8 or higher, in any id shape that contains claude--: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.", "model_info": { "supports_mid_conversation_system": true @@ -63553,7 +63920,13 @@ { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true @@ -63570,7 +63943,11 @@ { "name": "openai-reasoning-family-baseline", "pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))", - "fill_missing_for_providers": ["azure", "azure_ai", "openai"], + "fill_missing_for_providers": [ + "azure", + "azure_ai", + "openai" + ], "description": "OpenAI reasoning families by id shape, under any provider namespace and with an optional ft: prefix: the o-series (o1, o3-pro, o4-mini), gpt-5 through gpt-9 majors including dotted minors and suffixed variants (gpt-5.5-cyber, gpt-6-astra), and the codex, deep-research and chat-latest lines when standalone or on a gpt base. gpt-5-search-api is excluded because it is a search-only surface. Every model here is a reasoning model, and the Responses API drops the caller's reasoning param for any mapped OpenAI model whose info lacks supports_reasoning, so an id the registry has not named yet keeps its reasoning settings instead of silently losing them. Rules lose to exact entries. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", "model_info": { "supports_reasoning": true @@ -73263,7 +73640,9 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_regions": ["global"], + "supported_regions": [ + "global" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -74604,7 +74983,9 @@ }, "global.xai.grok-4.7": { "supports_regex_lookaround": false, - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 5e-07, @@ -74630,7 +75011,9 @@ }, "us.xai.grok-4.7": { "supports_regex_lookaround": false, - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 5.5e-07, @@ -75079,7 +75462,11 @@ "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "rpm": 1000.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -75124,7 +75511,11 @@ "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -75170,7 +75561,11 @@ "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -75252,7 +75647,7 @@ "supports_tool_choice": true, "supports_vision": true }, -"claude-haiku-5-5": { + "claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, @@ -76179,7 +76574,11 @@ "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76225,7 +76624,11 @@ "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76279,7 +76682,11 @@ "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 4096.0, "rpm": 2000.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76338,7 +76745,11 @@ "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76396,7 +76807,11 @@ "output_cost_per_token_priority": 3.6e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76624,7 +77039,11 @@ "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, - "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, + "search_context_cost_per_query": { + "search_context_size_high": 0.02, + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, @@ -76988,5 +77407,605 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "bedrock/claude_platform/claude-fable-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-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_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/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-fable-5-1": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-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/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_computer_use": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "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, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": 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, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 + }, + "bedrock/claude_platform/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-7": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": 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": 2048, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-8": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": 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": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": 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, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-5-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "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_native_structured_output": 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, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "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, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "provider_specific_entry": { + "us": 1.1 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": 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": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": 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, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 98fee42de3c..583b8cb2b8e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8899,7 +8899,11 @@ "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8952,7 +8956,11 @@ "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -9644,7 +9652,11 @@ "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, "output_cost_per_token_priority": 2.2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -16419,7 +16431,10 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "provider_specific_entry": {"us":1.1,"fast":2}, + "provider_specific_entry": { + "us": 1.1, + "fast": 2 + }, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, @@ -28970,7 +28985,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -29085,7 +29104,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -29138,7 +29161,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { @@ -29189,7 +29216,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -29233,7 +29264,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { @@ -29329,7 +29364,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29391,7 +29430,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -29452,7 +29495,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29539,7 +29586,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, @@ -29594,7 +29645,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -29641,7 +29696,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -29829,7 +29888,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, + "search_free_requests": { + "count": 10000, + "period": "day", + "shared_group": "gemini-2.5-pro" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, @@ -29866,8 +29929,16 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29948,7 +30019,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30005,7 +30080,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { @@ -30029,8 +30108,16 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30113,7 +30200,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -30179,7 +30270,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30241,7 +30336,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30267,8 +30366,16 @@ "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30415,8 +30522,16 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30503,7 +30618,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30831,7 +30950,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -30876,7 +30999,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -30938,7 +31065,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -31088,7 +31219,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, @@ -31201,7 +31336,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "supports_reasoning": true }, @@ -31265,8 +31404,16 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "rpm": 1000.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -31343,7 +31490,11 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "rpm": 1000.0, - "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_context_cost_per_query": { + "search_context_size_low": 0.035, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.035 + }, "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", @@ -31417,7 +31568,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, + "search_free_requests": { + "count": 1500, + "period": "day", + "shared_group": "gemini-2-flash" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, "input_cost_per_audio_token_priority": 5.4e-07, @@ -31623,7 +31778,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, + "search_free_requests": { + "count": 10000, + "period": "day", + "shared_group": "gemini-2.5-pro" + }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -31721,7 +31880,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07, @@ -31784,7 +31947,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -31841,7 +32008,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -31905,7 +32076,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -31972,7 +32147,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32035,7 +32214,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32098,7 +32281,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32194,7 +32381,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -32258,7 +32449,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -32286,8 +32481,16 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -32402,7 +32605,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -32468,7 +32675,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32530,7 +32741,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -32555,8 +32770,16 @@ "output_cost_per_token_flex": 1.875e-06, "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -41522,7 +41745,7 @@ "supports_xhigh_reasoning_effort": true }, "meta/muse-voice-transcribe-1.0": { - "input_cost_per_second": 0.00005, + "input_cost_per_second": 5e-05, "litellm_provider": "meta", "mode": "audio_transcription", "source": "https://dev.meta.ai/docs/speech-to-text", @@ -52343,7 +52566,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -52377,7 +52599,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, @@ -52410,7 +52631,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -52435,7 +52655,6 @@ "/v1/images/edits", "/v1/batch" ] - }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, @@ -52530,7 +52749,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -52593,7 +52816,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -52655,7 +52882,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "search_free_requests": { + "count": 5000, + "period": "month", + "shared_group": "gemini-3" + }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -61612,11 +61843,41 @@ "output_cost_per_second_480p": 0.096075, "output_cost_per_second_720p": 0.216, "output_cost_per_second_1080p": 0.5346, - "supported_modalities": ["text", "image", "video", "audio"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "854x480", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "480x854", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "volcengine/doubao-seedance-2-0-260128": { "litellm_provider": "volcengine", @@ -61627,11 +61888,41 @@ "output_cost_per_second_720p": 0.141942857, "output_cost_per_second_1080p": 0.354085714, "output_cost_per_second_4k": 0.722057143, - "supported_modalities": ["text", "image", "video", "audio"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "864x496", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "496x864", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "volcengine/doubao-seedance-2-0-fast-260128": { "litellm_provider": "volcengine", @@ -61640,11 +61931,41 @@ "output_cost_per_second": 0.114171429, "output_cost_per_second_480p": 0.053089714, "output_cost_per_second_720p": 0.114171429, - "supported_modalities": ["text", "image", "video", "audio"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "864x496", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "496x864", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "volcengine/doubao-seedance-2-0-mini-260615": { "litellm_provider": "volcengine", @@ -61653,11 +61974,39 @@ "output_cost_per_second": 0.070971429, "output_cost_per_second_480p": 0.033001714, "output_cost_per_second_720p": 0.070971429, - "supported_modalities": ["text", "image"], - "supported_output_modalities": ["video"], - "supported_endpoints": ["/v1/videos"], - "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, - "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "volcengine_video_frames": { + "480p": { + "16:9": "864x496", + "4:3": "752x560", + "1:1": "640x640", + "3:4": "560x752", + "9:16": "496x864", + "21:9": "992x432" + }, + "720p": { + "16:9": "1280x720", + "4:3": "1112x834", + "1:1": "960x960", + "3:4": "834x1112", + "9:16": "720x1280", + "21:9": "1470x630" + } + } + }, + "metadata": { + "comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card." + } }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, @@ -63518,7 +63867,13 @@ { "name": "claude-adaptive-thinking", "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.6 or higher, in any id shape that contains claude--: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Turns on adaptive thinking for new versions and new families with no code change.", "model_info": { "supports_adaptive_thinking": true @@ -63527,7 +63882,13 @@ { "name": "claude-legacy-thinking", "pattern": "claude-[a-z]+-4[-._]6(?!\\d)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.6 exactly, in any id shape that contains claude--4-6 (dotted and underscored minors included, dated releases such as claude-sonnet-4-6-20260219 too). The 4.6 family is adaptive-thinking yet still accepts legacy thinking.type=enabled with budget_tokens, so the caller's hard budget cap is forwarded verbatim instead of being rewritten to an uncapped output_config.effort. The lookahead keeps two-digit minors such as 4-60 from matching. 4.7+ and 5+ majors reject the legacy shape and stay on the adaptive translation.", "model_info": { "supports_legacy_thinking": true @@ -63544,7 +63905,13 @@ { "name": "claude-mid-conversation-system", "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.8 or higher, in any id shape that contains claude--: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.", "model_info": { "supports_mid_conversation_system": true @@ -63553,7 +63920,13 @@ { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "fill_missing_for_providers": [ + "anthropic", + "azure_ai", + "bedrock", + "bedrock_converse", + "vertex_ai-anthropic_models" + ], "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true @@ -63570,7 +63943,11 @@ { "name": "openai-reasoning-family-baseline", "pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))", - "fill_missing_for_providers": ["azure", "azure_ai", "openai"], + "fill_missing_for_providers": [ + "azure", + "azure_ai", + "openai" + ], "description": "OpenAI reasoning families by id shape, under any provider namespace and with an optional ft: prefix: the o-series (o1, o3-pro, o4-mini), gpt-5 through gpt-9 majors including dotted minors and suffixed variants (gpt-5.5-cyber, gpt-6-astra), and the codex, deep-research and chat-latest lines when standalone or on a gpt base. gpt-5-search-api is excluded because it is a search-only surface. Every model here is a reasoning model, and the Responses API drops the caller's reasoning param for any mapped OpenAI model whose info lacks supports_reasoning, so an id the registry has not named yet keeps its reasoning settings instead of silently losing them. Rules lose to exact entries. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", "model_info": { "supports_reasoning": true @@ -73263,7 +73640,9 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_regions": ["global"], + "supported_regions": [ + "global" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -74604,7 +74983,9 @@ }, "global.xai.grok-4.7": { "supports_regex_lookaround": false, - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 5e-07, @@ -74630,7 +75011,9 @@ }, "us.xai.grok-4.7": { "supports_regex_lookaround": false, - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 5.5e-07, @@ -75079,7 +75462,11 @@ "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "rpm": 1000.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -75124,7 +75511,11 @@ "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -75170,7 +75561,11 @@ "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -75252,7 +75647,7 @@ "supports_tool_choice": true, "supports_vision": true }, -"claude-haiku-5-5": { + "claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, @@ -76179,7 +76574,11 @@ "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76225,7 +76624,11 @@ "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76279,7 +76682,11 @@ "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 4096.0, "rpm": 2000.0, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76338,7 +76745,11 @@ "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76396,7 +76807,11 @@ "output_cost_per_token_priority": 3.6e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -76624,7 +77039,11 @@ "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, - "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, + "search_context_cost_per_query": { + "search_context_size_high": 0.02, + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, @@ -76988,5 +77407,605 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "bedrock/claude_platform/claude-fable-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-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_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/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-fable-5-1": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-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/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_computer_use": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "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, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": 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, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 + }, + "bedrock/claude_platform/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-7": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": 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": 2048, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-8": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": 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": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": 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, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-5-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "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_native_structured_output": 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, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "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, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "provider_specific_entry": { + "us": 1.1 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": 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": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": 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, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true } } diff --git a/tests/unit/llms/bedrock/test_cost_calculation.py b/tests/unit/llms/bedrock/test_cost_calculation.py new file mode 100644 index 00000000000..80465cab5fe --- /dev/null +++ b/tests/unit/llms/bedrock/test_cost_calculation.py @@ -0,0 +1,41 @@ +import json +from importlib.resources import files +from typing import Final + +import pytest + +import litellm +from litellm.types.utils import Usage + +CLAUDE_PLATFORM_PREFIX: Final = "bedrock/claude_platform/" +CLAUDE_PLATFORM_KEYS: Final = tuple( + key + for key in json.loads(files("litellm").joinpath("model_prices_and_context_window_backup.json").read_text()) + if key.startswith(CLAUDE_PLATFORM_PREFIX) +) + + +def test_claude_platform_rows_exist() -> None: + assert CLAUDE_PLATFORM_KEYS + + +@pytest.mark.parametrize("inference_geo", ["global", "us"]) +@pytest.mark.parametrize("key", CLAUDE_PLATFORM_KEYS) +def test_claude_platform_cost_matches_claude_api_cost(local_model_cost_map: None, key: str, inference_geo: str) -> None: + usage: Final = Usage( + prompt_tokens=1_000, + completion_tokens=200, + cache_read_input_tokens=300, + cache_creation_input_tokens=250, + inference_geo=inference_geo, + ) + + claude_platform_cost: Final = litellm.cost_per_token( + model=key.removeprefix("bedrock/"), custom_llm_provider="bedrock", usage_object=usage + ) + claude_api_cost: Final = litellm.cost_per_token( + model=key.removeprefix(CLAUDE_PLATFORM_PREFIX), custom_llm_provider="anthropic", usage_object=usage + ) + + assert claude_platform_cost == pytest.approx(claude_api_cost) + assert sum(claude_platform_cost) > 0 diff --git a/tests/unit/test_utils_get_model_info.py b/tests/unit/test_utils_get_model_info.py index bfaac44a483..8a1266a5e16 100644 --- a/tests/unit/test_utils_get_model_info.py +++ b/tests/unit/test_utils_get_model_info.py @@ -136,6 +136,7 @@ def _enforce_bedrock_converse_models( info.get("litellm_provider") == "bedrock" and info.get("mode") == "chat" and model not in whitelist_models + and BedrockModelInfo.get_bedrock_route(model) != "claude_platform" and not ( (base_model := BedrockModelInfo.get_base_model(model)) != model and model_cost.get(base_model, {}).get("litellm_provider") == "bedrock_converse"