From 3afe779125d27448ae4854ba91ee5626cdc497bf Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 16:07:22 +0000 Subject: [PATCH] fix(cost-map): rolling provider pricing, capability and retirement audit (#48188) * fix(cost-map): registry audit 2026-10-24, add provider retirement dates and fix mistral-large-4 and azure_ai sonnet 5.5 prices Co-authored-by: Hannes Brantner Co-authored-by: Aasif-Simpplr Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(mistral): derive mistral-large-4 cost expectations from the registry row instead of pinned prices Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): add fireworks spot routers and reprice together Qwen3.7-Max Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): absorb open registry PRs and update azure_ai mistral-small-2503 retirement date Co-authored-by: kerry Co-authored-by: Aryan Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * chore(cost-map): credit absorbed registry PR authors Co-authored-by: kerry Co-authored-by: Aryan Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): add azure gpt-6.1-terra rows and fireworks models/rune path Co-authored-by: ceng-p Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): add azure_ai gpt-6.1-terra global standard row Co-authored-by: Ahmet Selim FEDAKAR <122402435+selimfedakar@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): price mistral-large-4 cache reads at the published $0.14 Co-authored-by: zoveki <349028329+zoveki@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * revert(cost-map): leave mistral-large-4 rows to #48825 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost-map): refresh provider pricing and retirement metadata Absorb the verified GPT-5.6 Terra and Luna price fields from #48709. Add official Groq caching, xAI batch pricing, Moonshot metadata, and retirement dates without replacing existing model entries. Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Hannes Brantner Co-authored-by: Aasif-Simpplr Co-authored-by: Aryan Co-authored-by: kerry Co-authored-by: ceng-p Co-authored-by: Ahmet Selim FEDAKAR <122402435+selimfedakar@users.noreply.github.com> Co-authored-by: zoveki <349028329+zoveki@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 1125 ++++++++++++++--- model_prices_and_context_window.json | 1125 ++++++++++++++--- .../test_tool_call_cost_tracking.py | 119 +- .../test_model_prices_and_context_window.py | 40 +- 4 files changed, 1973 insertions(+), 436 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9c3bd9dacbb..5a7006de2cf 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4039,6 +4039,7 @@ "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { + "deprecation_date": "2027-09-15", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "azure_ai", @@ -4243,6 +4244,54 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, @@ -4904,6 +4953,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4922,6 +4976,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5009,6 +5068,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5048,6 +5112,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5113,6 +5182,11 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { @@ -5188,6 +5262,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5344,6 +5423,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -5428,6 +5512,11 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { @@ -5680,6 +5769,11 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5717,6 +5811,11 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5754,6 +5853,11 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5791,6 +5895,11 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6203,6 +6312,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -6221,6 +6335,11 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -6710,6 +6829,11 @@ "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 @@ -6797,6 +6921,11 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6835,6 +6964,11 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6906,6 +7040,11 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6944,6 +7083,11 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6981,6 +7125,11 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7016,6 +7165,11 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7051,6 +7205,11 @@ "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -7112,6 +7271,11 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5-chat": { @@ -7459,6 +7623,11 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7498,6 +7667,11 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7567,6 +7741,11 @@ "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -7599,9 +7778,9 @@ "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7637,9 +7816,9 @@ "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7996,9 +8175,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8043,9 +8222,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8095,9 +8274,9 @@ "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -8157,9 +8336,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8220,9 +8399,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 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 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8283,9 +8462,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8346,9 +8525,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8409,9 +8588,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8472,9 +8651,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -8519,9 +8698,9 @@ "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8567,9 +8746,9 @@ "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8615,9 +8794,9 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -8663,9 +8842,9 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -8718,7 +8897,7 @@ "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":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "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", @@ -8770,7 +8949,7 @@ "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":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "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", @@ -8800,6 +8979,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -8815,9 +9041,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8863,9 +9089,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8896,6 +9122,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/us/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/us/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, @@ -8911,9 +9184,9 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8944,6 +9217,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/eu/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/eu/gpt-6.1-sol": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, @@ -8959,9 +9279,9 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8992,6 +9312,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/apac/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/apac/gpt-6.1-sol": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, @@ -9007,9 +9374,9 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -9134,9 +9501,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9188,9 +9555,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9243,9 +9610,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9298,9 +9665,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9345,9 +9712,9 @@ "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9393,9 +9760,9 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -9448,7 +9815,7 @@ "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":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "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", @@ -9536,9 +9903,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9590,9 +9957,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9645,9 +10012,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9700,9 +10067,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9760,9 +10127,9 @@ "output_cost_per_token_above_272k_tokens_priority": 9e-05, "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9814,9 +10181,9 @@ "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9868,9 +10235,9 @@ "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9921,9 +10288,9 @@ "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9981,9 +10348,9 @@ "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10034,9 +10401,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10086,9 +10453,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10139,9 +10506,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10191,9 +10558,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10239,9 +10606,9 @@ "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -10282,9 +10649,9 @@ "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -10322,9 +10689,9 @@ "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10372,9 +10739,9 @@ "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10423,9 +10790,9 @@ "mode": "chat", "output_cost_per_token": 1.25e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10470,9 +10837,9 @@ "mode": "chat", "output_cost_per_token": 1.25e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10934,6 +11301,11 @@ "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10965,6 +11337,11 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -10996,9 +11373,9 @@ "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -11065,6 +11442,11 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", @@ -11095,6 +11477,11 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", @@ -11124,6 +11511,11 @@ "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -11155,6 +11547,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11268,6 +11665,11 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11305,6 +11707,11 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11428,6 +11835,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -11446,6 +11858,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -11533,6 +11950,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11572,6 +11994,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11608,6 +12035,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11673,6 +12105,11 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { @@ -11800,6 +12237,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11832,6 +12274,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11898,6 +12345,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11918,6 +12370,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11935,6 +12392,7 @@ "output_cost_per_second": 0.0001 }, "azure_ai/Cohere-embed-v3-english": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, @@ -11945,6 +12403,7 @@ "supports_embedding_image_input": true }, "azure_ai/Cohere-embed-v3-multilingual": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, @@ -11955,6 +12414,7 @@ "supports_embedding_image_input": true }, "azure_ai/Codestral-2501": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, @@ -11974,6 +12434,7 @@ "supports_native_streaming": true }, "azure_ai/FLUX-1.1-pro": { + "deprecation_date": "2027-01-05", "litellm_provider": "azure_ai", "max_input_tokens": 5000, "mode": "image_generation", @@ -11984,6 +12445,7 @@ ] }, "azure_ai/FLUX.1-Kontext-pro": { + "deprecation_date": "2027-01-05", "litellm_provider": "azure_ai", "max_input_tokens": 5000, "mode": "image_generation", @@ -11994,6 +12456,7 @@ ] }, "azure_ai/flux.2-pro": { + "deprecation_date": "2027-01-20", "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", @@ -12004,6 +12467,7 @@ ] }, "azure_ai/FLUX.2-flex": { + "deprecation_date": "2027-01-20", "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -12368,6 +12832,7 @@ "supports_tool_choice": true }, "azure_ai/Llama-3.3-70B-Instruct": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12379,6 +12844,7 @@ "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "deprecation_date": "2026-11-19", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, @@ -12391,6 +12857,7 @@ "supports_vision": true }, "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, @@ -12624,6 +13091,7 @@ ] }, "azure_ai/cohere-command-a": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -12696,6 +13164,7 @@ "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v4.0-pro": { + "deprecation_date": "2027-09-13", "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12706,6 +13175,7 @@ "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/cohere-rerank-v4.0-fast": { + "deprecation_date": "2027-09-13", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12716,6 +13186,7 @@ "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/deepseek-v3.2": { + "deprecation_date": "2027-11-01", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12730,6 +13201,7 @@ "supports_tool_choice": true }, "azure_ai/deepseek-v3.2-speciale": { + "deprecation_date": "2027-11-01", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12800,6 +13272,7 @@ "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { + "deprecation_date": "2027-06-01", "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12818,6 +13291,7 @@ "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, @@ -12906,6 +13380,7 @@ "supports_web_search": true }, "azure_ai/grok-4-1-fast-non-reasoning": { + "deprecation_date": "2027-05-19", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -12919,6 +13394,7 @@ "supports_web_search": true }, "azure_ai/grok-4-1-fast-reasoning": { + "deprecation_date": "2027-05-19", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -12933,6 +13409,7 @@ "supports_web_search": true }, "azure_ai/grok-code-fast-1": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, @@ -13100,7 +13577,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { - "deprecation_date": "2026-12-09", + "deprecation_date": "2027-02-15", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -14619,11 +15096,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14638,6 +15116,7 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" @@ -14647,11 +15126,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14665,7 +15145,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md" }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -14787,11 +15268,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14806,6 +15288,7 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" @@ -14815,11 +15298,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14833,7 +15317,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md" }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -15197,6 +15682,7 @@ "supports_tool_choice": true }, "cerebras/llama-3.3-70b": { + "deprecation_date": "2026-02-16", "input_cost_per_token": 8.5e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15207,6 +15693,7 @@ "supports_tool_choice": true }, "cerebras/llama3.1-70b": { + "deprecation_date": "2025-01-17", "input_cost_per_token": 6e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15217,6 +15704,7 @@ "supports_tool_choice": true }, "cerebras/llama3.1-8b": { + "deprecation_date": "2026-05-27", "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15241,6 +15729,7 @@ "supports_tool_choice": true }, "cerebras/qwen-3-32b": { + "deprecation_date": "2026-02-16", "input_cost_per_token": 4e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15552,6 +16041,7 @@ "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, @@ -15570,7 +16060,8 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_batches": 7.5e-06 + "output_cost_per_token_batches": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md" }, "claude-opus-4-5-20251101": { "supports_web_search": true, @@ -21638,10 +22129,10 @@ "supports_vision": true }, "databricks/databricks-gpt-5-6-terra": { - "cache_creation_input_token_cost": 3.12501e-06, - "cache_read_input_token_cost": 2.4997e-07, - "input_cost_per_token": 2.49998e-06, - "input_dbu_cost_per_token": 3.5714e-05, + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -21649,8 +22140,8 @@ "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.500002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.200003e-05, + "output_dbu_cost_per_token": 0.000171429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -21666,10 +22157,10 @@ "supports_vision": true }, "databricks/databricks-gpt-5-6-luna": { - "cache_creation_input_token_cost": 1.24999e-06, - "cache_read_input_token_cost": 1.0003e-07, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, + "cache_creation_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 1.9999e-07, + "input_dbu_cost_per_token": 2.857e-06, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -21677,8 +22168,8 @@ "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 5.99998e-06, - "output_dbu_cost_per_token": 8.5714e-05, + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -26989,6 +27480,18 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash": { + "cache_read_input_token_cost": 2.1e-08, + "input_cost_per_token": 1.05e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.1e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "cache_read_input_token_cost_priority": 5.5e-08, @@ -34476,6 +34979,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-tts": { + "deprecation_date": "2027-01-06", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -35093,6 +35597,7 @@ "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2026-12-11", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -35349,6 +35854,7 @@ "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-04-01", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", @@ -35648,15 +36154,15 @@ "gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_12hr": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.0001, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.0003, - "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-05, "cache_creation_input_token_cost_above_12hr_priority": 5e-05, - "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-05, @@ -35826,11 +36332,11 @@ "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_12hr": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-06, - "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-07, "cache_creation_input_token_cost_above_12hr_priority": 5e-07, "cache_creation_input_token_cost_decisions": 1.25e-07, @@ -37073,6 +37579,7 @@ "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2027-04-01", "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, @@ -37120,6 +37627,7 @@ "supports_minimal_reasoning_effort": false }, "gpt-5-pro": { + "deprecation_date": "2026-12-11", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", @@ -37399,6 +37907,7 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-12-11", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -37499,6 +38008,7 @@ "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, + "deprecation_date": "2026-12-11", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, @@ -38208,6 +38718,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -38228,6 +38739,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -38247,6 +38759,7 @@ "search_context_size_medium": 0.005 }, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -41919,6 +42432,7 @@ }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2026-08-31", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, @@ -41949,7 +42463,31 @@ "supports_video_input": true, "supports_vision": true }, + "moonshot/kimi-k3.1-pro": { + "cache_creation_input_token_cost": 2e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, "moonshot/kimi-k3": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "moonshot", @@ -41964,6 +42502,7 @@ ], "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -41971,6 +42510,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-128k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -41983,6 +42523,7 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -41996,6 +42537,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-32k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -42008,6 +42550,7 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -42021,6 +42564,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-8k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -42033,6 +42577,7 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -42046,6 +42591,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-auto": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -43238,6 +43784,7 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, @@ -43428,6 +43975,7 @@ "supports_vision": false }, "o3-pro": { + "deprecation_date": "2026-12-11", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", @@ -47288,13 +47836,13 @@ "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 7.5e-06, "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, @@ -47804,6 +48352,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -47822,7 +48371,7 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" @@ -52899,15 +53448,21 @@ "xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 8e-07, + "cache_read_input_token_cost_batches": 4e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 3.2e-06, + "input_cost_per_token_batches": 1.6e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, + "output_cost_per_token_above_200k_tokens_batches": 9.6e-06, + "output_cost_per_token_batches": 4.8e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -56988,6 +57543,7 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { + "deprecation_date": "2027-02-26", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, @@ -61796,6 +62352,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, "cache_read_input_token_cost_priority": 1.125e-08, @@ -61856,6 +62424,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/kimi-k3-spot": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": true + }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, @@ -64525,6 +65105,7 @@ ] }, "xai/grok-imagine-image-pro": { + "deprecation_date": "2026-05-15", "input_cost_per_image": 0.05, "litellm_provider": "xai", "mode": "image_generation", @@ -65054,6 +65635,18 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-spot": { + "cache_read_input_token_cost": 1.82e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, "cache_read_input_token_cost_priority": 4.875e-07, @@ -65362,6 +65955,7 @@ ] }, "scaleway/glm-5.2": { + "deprecation_date": "2026-11-16", "input_cost_per_token": 1.8e-06, "litellm_provider": "scaleway", "max_input_tokens": 256000, @@ -67920,6 +68514,11 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { @@ -67934,6 +68533,11 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { @@ -67972,6 +68576,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { @@ -67996,6 +68605,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { @@ -68008,6 +68622,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { @@ -68018,6 +68637,11 @@ "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { @@ -68042,6 +68666,11 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { @@ -68060,6 +68689,11 @@ "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { @@ -68072,6 +68706,11 @@ "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { @@ -68087,6 +68726,11 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { @@ -68099,6 +68743,11 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { @@ -68113,6 +68762,11 @@ "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-6-astra": { @@ -68129,6 +68783,11 @@ "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_above_272k_tokens": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/chat/completions", @@ -68173,9 +68832,9 @@ "output_cost_per_token": 6e-07, "output_cost_per_token_above_272k_tokens": 9e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -68221,9 +68880,9 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -68275,6 +68934,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { @@ -68288,6 +68952,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { @@ -68310,6 +68979,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { @@ -68323,6 +68997,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { @@ -68416,6 +69095,11 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { @@ -68430,6 +69114,11 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { @@ -68468,6 +69157,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { @@ -68492,6 +69186,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { @@ -68504,6 +69203,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { @@ -68514,6 +69218,11 @@ "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { @@ -68538,6 +69247,11 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { @@ -68556,6 +69270,11 @@ "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { @@ -68568,6 +69287,11 @@ "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { @@ -68583,6 +69307,11 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { @@ -68595,6 +69324,11 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { @@ -68609,6 +69343,11 @@ "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-mini": { @@ -68655,7 +69394,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2026-10-31", + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, @@ -71000,6 +71739,7 @@ "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "deprecation_date": "2026-05-15", "input_cost_per_image_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_above_200k_tokens": 2e-06, @@ -71896,7 +72636,7 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "deprecation_date": "2027-09-29", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", @@ -72503,15 +73243,15 @@ "gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 6e-05, - "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, "cache_creation_input_token_cost_above_12hr_priority": 1e-05, - "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, @@ -74472,14 +75212,14 @@ "supports_vision": true }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "max_output_tokens": 943718, "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints", + "output_cost_per_token": 1.5e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -74577,6 +75317,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": true + }, "github_copilot/claude-sonnet-4.6": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -76331,6 +77083,15 @@ "max" ] }, + "fireworks_ai/accounts/fireworks/models/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" + }, "bedrock_mantle/openai.gpt-6.1-terra": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9c3bd9dacbb..5a7006de2cf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4039,6 +4039,7 @@ "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { + "deprecation_date": "2027-09-15", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "azure_ai", @@ -4243,6 +4244,54 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, @@ -4904,6 +4953,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4922,6 +4976,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5009,6 +5068,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5048,6 +5112,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5113,6 +5182,11 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { @@ -5188,6 +5262,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5344,6 +5423,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -5428,6 +5512,11 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { @@ -5680,6 +5769,11 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5717,6 +5811,11 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5754,6 +5853,11 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5791,6 +5895,11 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6203,6 +6312,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -6221,6 +6335,11 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -6710,6 +6829,11 @@ "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 @@ -6797,6 +6921,11 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6835,6 +6964,11 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6906,6 +7040,11 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6944,6 +7083,11 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6981,6 +7125,11 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7016,6 +7165,11 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7051,6 +7205,11 @@ "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -7112,6 +7271,11 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5-chat": { @@ -7459,6 +7623,11 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7498,6 +7667,11 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7567,6 +7741,11 @@ "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -7599,9 +7778,9 @@ "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7637,9 +7816,9 @@ "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7996,9 +8175,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8043,9 +8222,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8095,9 +8274,9 @@ "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -8157,9 +8336,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8220,9 +8399,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 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 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8283,9 +8462,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8346,9 +8525,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8409,9 +8588,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8472,9 +8651,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -8519,9 +8698,9 @@ "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8567,9 +8746,9 @@ "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8615,9 +8794,9 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -8663,9 +8842,9 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -8718,7 +8897,7 @@ "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":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "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", @@ -8770,7 +8949,7 @@ "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":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "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", @@ -8800,6 +8979,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -8815,9 +9041,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8863,9 +9089,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8896,6 +9122,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/us/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/us/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, @@ -8911,9 +9184,9 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8944,6 +9217,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/eu/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/eu/gpt-6.1-sol": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, @@ -8959,9 +9279,9 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8992,6 +9312,53 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/apac/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/apac/gpt-6.1-sol": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, @@ -9007,9 +9374,9 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -9134,9 +9501,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9188,9 +9555,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9243,9 +9610,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9298,9 +9665,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9345,9 +9712,9 @@ "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9393,9 +9760,9 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -9448,7 +9815,7 @@ "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":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "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", @@ -9536,9 +9903,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9590,9 +9957,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9645,9 +10012,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9700,9 +10067,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9760,9 +10127,9 @@ "output_cost_per_token_above_272k_tokens_priority": 9e-05, "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9814,9 +10181,9 @@ "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9868,9 +10235,9 @@ "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9921,9 +10288,9 @@ "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9981,9 +10348,9 @@ "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10034,9 +10401,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10086,9 +10453,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10139,9 +10506,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10191,9 +10558,9 @@ "max_output_tokens": 128000, "mode": "chat", "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10239,9 +10606,9 @@ "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -10282,9 +10649,9 @@ "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -10322,9 +10689,9 @@ "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10372,9 +10739,9 @@ "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10423,9 +10790,9 @@ "mode": "chat", "output_cost_per_token": 1.25e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10470,9 +10837,9 @@ "mode": "chat", "output_cost_per_token": 1.25e-06, "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_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10934,6 +11301,11 @@ "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10965,6 +11337,11 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -10996,9 +11373,9 @@ "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -11065,6 +11442,11 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", @@ -11095,6 +11477,11 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", @@ -11124,6 +11511,11 @@ "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -11155,6 +11547,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11268,6 +11665,11 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11305,6 +11707,11 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11428,6 +11835,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -11446,6 +11858,11 @@ "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -11533,6 +11950,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11572,6 +11994,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11608,6 +12035,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11673,6 +12105,11 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { @@ -11800,6 +12237,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11832,6 +12274,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11898,6 +12345,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11918,6 +12370,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11935,6 +12392,7 @@ "output_cost_per_second": 0.0001 }, "azure_ai/Cohere-embed-v3-english": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, @@ -11945,6 +12403,7 @@ "supports_embedding_image_input": true }, "azure_ai/Cohere-embed-v3-multilingual": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, @@ -11955,6 +12414,7 @@ "supports_embedding_image_input": true }, "azure_ai/Codestral-2501": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, @@ -11974,6 +12434,7 @@ "supports_native_streaming": true }, "azure_ai/FLUX-1.1-pro": { + "deprecation_date": "2027-01-05", "litellm_provider": "azure_ai", "max_input_tokens": 5000, "mode": "image_generation", @@ -11984,6 +12445,7 @@ ] }, "azure_ai/FLUX.1-Kontext-pro": { + "deprecation_date": "2027-01-05", "litellm_provider": "azure_ai", "max_input_tokens": 5000, "mode": "image_generation", @@ -11994,6 +12456,7 @@ ] }, "azure_ai/flux.2-pro": { + "deprecation_date": "2027-01-20", "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", @@ -12004,6 +12467,7 @@ ] }, "azure_ai/FLUX.2-flex": { + "deprecation_date": "2027-01-20", "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -12368,6 +12832,7 @@ "supports_tool_choice": true }, "azure_ai/Llama-3.3-70B-Instruct": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12379,6 +12844,7 @@ "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "deprecation_date": "2026-11-19", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, @@ -12391,6 +12857,7 @@ "supports_vision": true }, "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, @@ -12624,6 +13091,7 @@ ] }, "azure_ai/cohere-command-a": { + "deprecation_date": "2027-02-15", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -12696,6 +13164,7 @@ "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v4.0-pro": { + "deprecation_date": "2027-09-13", "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12706,6 +13175,7 @@ "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/cohere-rerank-v4.0-fast": { + "deprecation_date": "2027-09-13", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12716,6 +13186,7 @@ "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/deepseek-v3.2": { + "deprecation_date": "2027-11-01", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12730,6 +13201,7 @@ "supports_tool_choice": true }, "azure_ai/deepseek-v3.2-speciale": { + "deprecation_date": "2027-11-01", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12800,6 +13272,7 @@ "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { + "deprecation_date": "2027-06-01", "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12818,6 +13291,7 @@ "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, @@ -12906,6 +13380,7 @@ "supports_web_search": true }, "azure_ai/grok-4-1-fast-non-reasoning": { + "deprecation_date": "2027-05-19", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -12919,6 +13394,7 @@ "supports_web_search": true }, "azure_ai/grok-4-1-fast-reasoning": { + "deprecation_date": "2027-05-19", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -12933,6 +13409,7 @@ "supports_web_search": true }, "azure_ai/grok-code-fast-1": { + "deprecation_date": "2027-01-31", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, @@ -13100,7 +13577,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { - "deprecation_date": "2026-12-09", + "deprecation_date": "2027-02-15", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -14619,11 +15096,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14638,6 +15116,7 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" @@ -14647,11 +15126,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14665,7 +15145,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md" }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -14787,11 +15268,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14806,6 +15288,7 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" @@ -14815,11 +15298,12 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-08", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14833,7 +15317,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md" }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -15197,6 +15682,7 @@ "supports_tool_choice": true }, "cerebras/llama-3.3-70b": { + "deprecation_date": "2026-02-16", "input_cost_per_token": 8.5e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15207,6 +15693,7 @@ "supports_tool_choice": true }, "cerebras/llama3.1-70b": { + "deprecation_date": "2025-01-17", "input_cost_per_token": 6e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15217,6 +15704,7 @@ "supports_tool_choice": true }, "cerebras/llama3.1-8b": { + "deprecation_date": "2026-05-27", "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15241,6 +15729,7 @@ "supports_tool_choice": true }, "cerebras/qwen-3-32b": { + "deprecation_date": "2026-02-16", "input_cost_per_token": 4e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -15552,6 +16041,7 @@ "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, @@ -15570,7 +16060,8 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_batches": 7.5e-06 + "output_cost_per_token_batches": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md" }, "claude-opus-4-5-20251101": { "supports_web_search": true, @@ -21638,10 +22129,10 @@ "supports_vision": true }, "databricks/databricks-gpt-5-6-terra": { - "cache_creation_input_token_cost": 3.12501e-06, - "cache_read_input_token_cost": 2.4997e-07, - "input_cost_per_token": 2.49998e-06, - "input_dbu_cost_per_token": 3.5714e-05, + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -21649,8 +22140,8 @@ "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.500002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.200003e-05, + "output_dbu_cost_per_token": 0.000171429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -21666,10 +22157,10 @@ "supports_vision": true }, "databricks/databricks-gpt-5-6-luna": { - "cache_creation_input_token_cost": 1.24999e-06, - "cache_read_input_token_cost": 1.0003e-07, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, + "cache_creation_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 1.9999e-07, + "input_dbu_cost_per_token": 2.857e-06, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -21677,8 +22168,8 @@ "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 5.99998e-06, - "output_dbu_cost_per_token": 8.5714e-05, + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -26989,6 +27480,18 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash": { + "cache_read_input_token_cost": 2.1e-08, + "input_cost_per_token": 1.05e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.1e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "cache_read_input_token_cost_priority": 5.5e-08, @@ -34476,6 +34979,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-tts": { + "deprecation_date": "2027-01-06", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -35093,6 +35597,7 @@ "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2026-12-11", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -35349,6 +35854,7 @@ "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-04-01", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", @@ -35648,15 +36154,15 @@ "gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_12hr": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.0001, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.0003, - "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-05, "cache_creation_input_token_cost_above_12hr_priority": 5e-05, - "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-05, @@ -35826,11 +36332,11 @@ "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_12hr": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-06, - "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-07, "cache_creation_input_token_cost_above_12hr_priority": 5e-07, "cache_creation_input_token_cost_decisions": 1.25e-07, @@ -37073,6 +37579,7 @@ "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2027-04-01", "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, @@ -37120,6 +37627,7 @@ "supports_minimal_reasoning_effort": false }, "gpt-5-pro": { + "deprecation_date": "2026-12-11", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", @@ -37399,6 +37907,7 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-12-11", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -37499,6 +38008,7 @@ "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, + "deprecation_date": "2026-12-11", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, @@ -38208,6 +38718,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -38228,6 +38739,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -38247,6 +38759,7 @@ "search_context_size_medium": 0.005 }, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -41919,6 +42432,7 @@ }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2026-08-31", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, @@ -41949,7 +42463,31 @@ "supports_video_input": true, "supports_vision": true }, + "moonshot/kimi-k3.1-pro": { + "cache_creation_input_token_cost": 2e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, "moonshot/kimi-k3": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "moonshot", @@ -41964,6 +42502,7 @@ ], "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -41971,6 +42510,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-128k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -41983,6 +42523,7 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -41996,6 +42537,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-32k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -42008,6 +42550,7 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -42021,6 +42564,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-8k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -42033,6 +42577,7 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -42046,6 +42591,7 @@ "supports_vision": true }, "moonshot/moonshot-v1-auto": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -43238,6 +43784,7 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, @@ -43428,6 +43975,7 @@ "supports_vision": false }, "o3-pro": { + "deprecation_date": "2026-12-11", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", @@ -47288,13 +47836,13 @@ "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 7.5e-06, "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, @@ -47804,6 +48352,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -47822,7 +48371,7 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" @@ -52899,15 +53448,21 @@ "xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 8e-07, + "cache_read_input_token_cost_batches": 4e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 3.2e-06, + "input_cost_per_token_batches": 1.6e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, + "output_cost_per_token_above_200k_tokens_batches": 9.6e-06, + "output_cost_per_token_batches": 4.8e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -56988,6 +57543,7 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { + "deprecation_date": "2027-02-26", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, @@ -61796,6 +62352,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, "cache_read_input_token_cost_priority": 1.125e-08, @@ -61856,6 +62424,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/kimi-k3-spot": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": true + }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, @@ -64525,6 +65105,7 @@ ] }, "xai/grok-imagine-image-pro": { + "deprecation_date": "2026-05-15", "input_cost_per_image": 0.05, "litellm_provider": "xai", "mode": "image_generation", @@ -65054,6 +65635,18 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-spot": { + "cache_read_input_token_cost": 1.82e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, "cache_read_input_token_cost_priority": 4.875e-07, @@ -65362,6 +65955,7 @@ ] }, "scaleway/glm-5.2": { + "deprecation_date": "2026-11-16", "input_cost_per_token": 1.8e-06, "litellm_provider": "scaleway", "max_input_tokens": 256000, @@ -67920,6 +68514,11 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { @@ -67934,6 +68533,11 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { @@ -67972,6 +68576,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { @@ -67996,6 +68605,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { @@ -68008,6 +68622,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { @@ -68018,6 +68637,11 @@ "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { @@ -68042,6 +68666,11 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { @@ -68060,6 +68689,11 @@ "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { @@ -68072,6 +68706,11 @@ "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { @@ -68087,6 +68726,11 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { @@ -68099,6 +68743,11 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { @@ -68113,6 +68762,11 @@ "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-6-astra": { @@ -68129,6 +68783,11 @@ "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_above_272k_tokens": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/chat/completions", @@ -68173,9 +68832,9 @@ "output_cost_per_token": 6e-07, "output_cost_per_token_above_272k_tokens": 9e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -68221,9 +68880,9 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -68275,6 +68934,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { @@ -68288,6 +68952,11 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { @@ -68310,6 +68979,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { @@ -68323,6 +68997,11 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { @@ -68416,6 +69095,11 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { @@ -68430,6 +69114,11 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { @@ -68468,6 +69157,11 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { @@ -68492,6 +69186,11 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { @@ -68504,6 +69203,11 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { @@ -68514,6 +69218,11 @@ "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { @@ -68538,6 +69247,11 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { @@ -68556,6 +69270,11 @@ "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { @@ -68568,6 +69287,11 @@ "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { @@ -68583,6 +69307,11 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { @@ -68595,6 +69324,11 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { @@ -68609,6 +69343,11 @@ "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-mini": { @@ -68655,7 +69394,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2026-10-31", + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, @@ -71000,6 +71739,7 @@ "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "deprecation_date": "2026-05-15", "input_cost_per_image_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_above_200k_tokens": 2e-06, @@ -71896,7 +72636,7 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "deprecation_date": "2027-09-29", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", @@ -72503,15 +73243,15 @@ "gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 6e-05, - "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, "cache_creation_input_token_cost_above_12hr_priority": 1e-05, - "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, @@ -74472,14 +75212,14 @@ "supports_vision": true }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "max_output_tokens": 943718, "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints", + "output_cost_per_token": 1.5e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -74577,6 +75317,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": true + }, "github_copilot/claude-sonnet-4.6": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -76331,6 +77083,15 @@ "max" ] }, + "fireworks_ai/accounts/fireworks/models/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" + }, "bedrock_mantle/openai.gpt-6.1-terra": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py index 7291c4858f6..e2452a928a4 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py @@ -1,4 +1,3 @@ - from typing import Final import pytest @@ -19,9 +18,7 @@ def test_web_search_cost_low(): web_search_options=web_search_options, model_info=model_info ) - assert ( - cost == model_info["search_context_cost_per_query"]["search_context_size_low"] - ) + assert cost == model_info["search_context_cost_per_query"]["search_context_size_low"] def test_web_search_cost_medium(): @@ -32,10 +29,7 @@ def test_web_search_cost_medium(): web_search_options=web_search_options, model_info=model_info ) - assert ( - cost - == model_info["search_context_cost_per_query"]["search_context_size_medium"] - ) + assert cost == model_info["search_context_cost_per_query"]["search_context_size_medium"] def test_web_search_cost_high(): @@ -46,9 +40,7 @@ def test_web_search_cost_high(): web_search_options=web_search_options, model_info=model_info ) - assert ( - cost == model_info["search_context_cost_per_query"]["search_context_size_high"] - ) + assert cost == model_info["search_context_cost_per_query"]["search_context_size_high"] def test_get_web_search_options_reads_tools_when_options_are_null() -> None: @@ -60,9 +52,7 @@ def test_get_web_search_options_reads_tools_when_options_are_null() -> None: def test_get_web_search_options_accepts_non_list_tool_iterables(): - options = StandardBuiltInToolCostTracking.get_web_search_options( - {"tools": ({"type": "web_search_preview"},)} - ) + options = StandardBuiltInToolCostTracking.get_web_search_options({"tools": ({"type": "web_search_preview"},)}) assert options == {"type": "web_search_preview"} @@ -76,25 +66,15 @@ def test_get_file_search_tool_call_does_not_validate_tool_payload(): # Test file search cost calculation def test_file_search_cost(): file_search = FileSearchTool(type="file_search") - cost = StandardBuiltInToolCostTracking.get_cost_for_file_search( - file_search=file_search - ) + cost = StandardBuiltInToolCostTracking.get_cost_for_file_search(file_search=file_search) assert cost == 0.0025 # $2.50/1000 calls = 0.0025 per call # Test edge cases def test_none_inputs(): # Test with None inputs - assert ( - StandardBuiltInToolCostTracking.get_cost_for_web_search( - web_search_options=None, model_info=None - ) - == 0.0 - ) - assert ( - StandardBuiltInToolCostTracking.get_cost_for_file_search(file_search=None) - == 0.0 - ) + assert StandardBuiltInToolCostTracking.get_cost_for_web_search(web_search_options=None, model_info=None) == 0.0 + assert StandardBuiltInToolCostTracking.get_cost_for_file_search(file_search=None) == 0.0 # Test the main get_cost_for_built_in_tools method @@ -119,9 +99,7 @@ def test_get_cost_for_built_in_tools_file_search(): Test that the cost for a file search is 0.00 when no response object is provided """ model = "gpt-4" - standard_built_in_tools_params = StandardBuiltInToolsParams( - file_search=FileSearchTool(type="file_search") - ) + standard_built_in_tools_params = StandardBuiltInToolsParams(file_search=FileSearchTool(type="file_search")) cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( model=model, @@ -144,9 +122,7 @@ def test_get_cost_for_anthropic_web_search_with_server_tool_use_dict(): usage = Usage(server_tool_use={"web_search_requests": 1}) assert isinstance(usage.server_tool_use, ServerToolUse) - assert StandardBuiltInToolCostTracking.response_object_includes_web_search_call( - response_object=None, usage=usage - ) + assert StandardBuiltInToolCostTracking.response_object_includes_web_search_call(response_object=None, usage=usage) def test_anthropic_web_search_zero_requests_from_raw_response_charges_zero(): @@ -257,9 +233,7 @@ def test_completion_cost_includes_web_search_without_standard_built_in_tools_par ) assert web_search_cost > 0, "Web search cost should be non-zero" - assert ( - cost >= web_search_cost - ), f"completion_cost ({cost}) should include web search cost ({web_search_cost})" + assert cost >= web_search_cost, f"completion_cost ({cost}) should include web search cost ({web_search_cost})" @pytest.mark.parametrize( @@ -286,18 +260,14 @@ def test_gemini_3x_web_search_billed_per_query(model, local_model_cost_map): web_search_requests = 2 model_info = litellm.get_model_info(model) assert model_info["web_search_billing_unit"] == "per_query" - per_query_cost = model_info["search_context_cost_per_query"][ - "search_context_size_medium" - ] + per_query_cost = model_info["search_context_cost_per_query"]["search_context_size_medium"] expected_cost = per_query_cost * web_search_requests usage = Usage( prompt_tokens=11, completion_tokens=100, total_tokens=111, - prompt_tokens_details=PromptTokensDetailsWrapper( - text_tokens=11, web_search_requests=web_search_requests - ), + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=11, web_search_requests=web_search_requests), ) cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( @@ -309,8 +279,7 @@ def test_gemini_3x_web_search_billed_per_query(model, local_model_cost_map): ) assert cost == pytest.approx(expected_cost), ( - f"Expected {web_search_requests} x ${per_query_cost} = ${expected_cost} " - f"per_query search fee, got ${cost}" + f"Expected {web_search_requests} x ${per_query_cost} = ${expected_cost} per_query search fee, got ${cost}" ) @@ -353,17 +322,13 @@ def test_gemini_2x_web_search_still_billed_per_prompt(local_model_cost_map): model = "vertex_ai/gemini-2.5-flash" model_info = litellm.get_model_info(model) assert not model_info.get("web_search_billing_unit") - expected_cost = model_info["search_context_cost_per_query"][ - "search_context_size_medium" - ] + expected_cost = model_info["search_context_cost_per_query"]["search_context_size_medium"] usage = Usage( prompt_tokens=11, completion_tokens=100, total_tokens=111, - prompt_tokens_details=PromptTokensDetailsWrapper( - text_tokens=11, web_search_requests=2 - ), + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=11, web_search_requests=2), ) cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( @@ -375,8 +340,7 @@ def test_gemini_2x_web_search_still_billed_per_prompt(local_model_cost_map): ) assert cost == pytest.approx(expected_cost), ( - f"Expected flat ${expected_cost} per_prompt search fee (2 queries clamped to 1), " - f"got ${cost}" + f"Expected flat ${expected_cost} per_prompt search fee (2 queries clamped to 1), got ${cost}" ) @@ -402,9 +366,7 @@ def test_web_search_provider_prefix_fallback_does_not_misprice_non_gemini_model( prompt_tokens=11, completion_tokens=100, total_tokens=111, - prompt_tokens_details=PromptTokensDetailsWrapper( - text_tokens=11, web_search_requests=2 - ), + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=11, web_search_requests=2), ) cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( @@ -427,7 +389,6 @@ def _openai_responses_with_web_search_calls(model, num_calls): ResponseFunctionWebSearch, ) - output = [ ResponseFunctionWebSearch( id=f"ws_{i}", @@ -458,9 +419,7 @@ def test_openai_responses_web_search_multiplied_by_call_count(local_model_cost_m from litellm.types.utils import Usage model = "gpt-4o-search-preview" - per_call = litellm.get_model_info(model)["search_context_cost_per_query"][ - "search_context_size_medium" - ] + per_call = litellm.get_model_info(model)["search_context_cost_per_query"]["search_context_size_medium"] usage = Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15) for num_calls in (1, 3): @@ -487,9 +446,7 @@ def test_web_search_call_count_reads_dict_output_items(local_model_cost_map): from litellm.types.utils import Usage model = "gpt-4o-search-preview" - per_call = litellm.get_model_info(model)["search_context_cost_per_query"][ - "search_context_size_medium" - ] + per_call = litellm.get_model_info(model)["search_context_cost_per_query"]["search_context_size_medium"] response = ResponsesAPIResponse.model_validate( { @@ -498,10 +455,7 @@ def test_web_search_call_count_reads_dict_output_items(local_model_cost_map): "model": model, "object": "response", "status": "completed", - "output": [ - {"type": "web_search_call", "id": f"ws_{i}", "status": "completed"} - for i in range(3) - ], + "output": [{"type": "web_search_call", "id": f"ws_{i}", "status": "completed"} for i in range(3)], } ) assert all(isinstance(item, dict) for item in response.output) @@ -514,9 +468,7 @@ def test_web_search_call_count_reads_dict_output_items(local_model_cost_map): standard_built_in_tools_params=None, ) - assert cost == pytest.approx(3 * per_call), ( - f"3 dict-shaped web searches must bill 3 x ${per_call}, got ${cost}" - ) + assert cost == pytest.approx(3 * per_call), f"3 dict-shaped web searches must bill 3 x ${per_call}, got ${cost}" # Note: File search integration test removed due to complex annotation detection logic @@ -596,8 +548,6 @@ _BEDROCK_MANTLE_WEB_SEARCH_MODELS = ( _BEDROCK_MANTLE_WEB_SEARCH_RATE = 0.012 - - def _openai_responses_response(model, output, usage=None, tools=None): return ResponsesAPIResponse.model_validate( { @@ -815,6 +765,31 @@ def test_responses_usage_tool_usage_web_search_billed_without_output_item(local_ assert cost == pytest.approx(num_requests * per_call) +@pytest.mark.parametrize("model", ["azure/gpt-5-mini", "azure/gpt-5.6-luna"]) +def test_azure_responses_web_search_billed_per_bing_request(local_model_cost_map, model): + """Azure OpenAI web_search is Grounding with Bing: $0.014 per reported Bing request, including rows + whose OpenAI twin prices search but the Azure row used to bill it at $0.""" + for num_requests in (1, 5): + response = _openai_responses_response( + model, + [dict(_ASSISTANT_MESSAGE_OUTPUT_ITEM)], + usage={ + "input_tokens": 10, + "output_tokens": 5, + "total_tokens": 15, + "tool_usage": {"web_search": {"num_requests": num_requests}}, + }, + ) + cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools( + model=model, + response_object=response, + usage=None, + custom_llm_provider="azure", + standard_built_in_tools_params=None, + ) + assert cost == pytest.approx(num_requests * 0.014) + + def _image_gen_token_usage(input_text, input_image, output_image, output_text): return { "input_tokens": 10, @@ -1012,6 +987,8 @@ def test_responses_image_gen_total_without_token_details_falls_back_to_per_image ) ) assert cost > 0 + + @pytest.mark.parametrize( ("model_key", "web_search_requests", "medium_cost_per_query", "expected_cost"), [ diff --git a/tests/unit/test_model_prices_and_context_window.py b/tests/unit/test_model_prices_and_context_window.py index 08a39b94c12..bbfe304429d 100644 --- a/tests/unit/test_model_prices_and_context_window.py +++ b/tests/unit/test_model_prices_and_context_window.py @@ -224,6 +224,41 @@ def test_dated_variants_carry_base_alias_service_tier_pricing(prices: dict): ) +# Azure OpenAI web_search runs on Grounding with Bing and bills each Bing request reported in +# tool_usage.web_search.num_requests: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/web-search +# Grounding with Bing lists $14 per 1,000 transactions: https://www.microsoft.com/en-us/bing/apis/grounding-pricing +AZURE_WEB_SEARCH_COST_PER_REQUEST: Final = 0.014 +_AZURE_DEPLOYMENT_PREFIX: Final = re.compile(r"^azure/(us/|eu/|global/|global-standard/)?") + + +def _azure_rows(prices: Mapping[str, object]) -> Mapping[str, dict]: + return MappingProxyType( + {key: row for key, row in prices.items() if key.startswith("azure/") and isinstance(row, dict)} + ) + + +def test_azure_web_search_rows_charge_the_grounding_with_bing_price(prices: dict): + wrong = { + key: row["search_context_cost_per_query"] + for key, row in _azure_rows(prices).items() + if row.get("search_context_cost_per_query") + and set(row["search_context_cost_per_query"].values()) != {AZURE_WEB_SEARCH_COST_PER_REQUEST} + } + assert wrong == {} + + +def test_azure_rows_price_web_search_when_their_openai_model_does(prices: dict): + missing = sorted( + key + for key, row in _azure_rows(prices).items() + if not row.get("search_context_cost_per_query") + and row.get("mode") in ("chat", "responses", None) + and isinstance(twin := prices.get(_AZURE_DEPLOYMENT_PREFIX.sub("", key)), dict) + and twin.get("search_context_cost_per_query") + ) + assert missing == [] + + PRIORITY_SUFFIX: Final = "_priority" MIN_PRIORITY_MARKUP: Final = 1.0 MAX_PRIORITY_MARKUP: Final = 5.0 @@ -845,7 +880,10 @@ def test_volcengine_doubao_seed_2_1_pro_260915_row_matches_published_metadata(pa assert entry["cache_read_input_token_cost"] == pytest.approx(1.2 / 6.9565 / 1_000_000, rel=1e-4) sibling = rows["volcengine/doubao-seed-2-1-pro-260628"] assert isinstance(sibling, dict) - assert all(entry[key] == sibling[key] for key in ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost")) + assert all( + entry[key] == sibling[key] + for key in ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost") + ) def _bedrock_gpt_oss_rows(prices: Mapping[str, JsonValue]) -> tuple[str, ...]: