From dc3a0399f23dfb2b34910868908887c9879f8ccc Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 00:36:08 +0000 Subject: [PATCH 01/19] chore(prices): sync Vertex AI prices: 4 models gemini-2.5-flash-preview-tts: output_cost_per_audio_token, input_cost_per_token_batches gemini/gemini-2.5-flash-preview-tts: output_cost_per_audio_token, input_cost_per_token_batches gemini-3.1-flash-live-preview: input_cost_per_second gemini/gemini-3.1-flash-live-preview: input_cost_per_second --- ...model_prices_and_context_window_backup.json | 18 ++++++++++++------ model_prices_and_context_window.json | 18 ++++++++++++------ 2 files changed, 24 insertions(+), 12 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9f91cf82f41..54f19419e47 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -26553,10 +26553,12 @@ }, "gemini/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/speech" ], @@ -55456,7 +55458,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55475,7 +55477,8 @@ "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "input_cost_per_second": 8.33333333333e-05 }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, @@ -55573,7 +55576,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55594,7 +55597,8 @@ "supports_web_search": true, "tpm": 250000, "rpm": 10, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "input_cost_per_second": 8.33333333333e-05 }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, @@ -55613,10 +55617,12 @@ }, "gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/speech" ] diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9f91cf82f41..54f19419e47 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26553,10 +26553,12 @@ }, "gemini/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/speech" ], @@ -55456,7 +55458,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55475,7 +55477,8 @@ "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "input_cost_per_second": 8.33333333333e-05 }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, @@ -55573,7 +55576,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55594,7 +55597,8 @@ "supports_web_search": true, "tpm": 250000, "rpm": 10, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "input_cost_per_second": 8.33333333333e-05 }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, @@ -55613,10 +55617,12 @@ }, "gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/speech" ] From 01b069eb6c1cb8280f9600f1a2d1ec22cb257e29 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 01:36:09 +0000 Subject: [PATCH 02/19] chore(prices): sync AWS Bedrock prices: 25 models anthropic.claude-fable-5: anthropic.claude-fable-5-1: anthropic.claude-opus-4-7: anthropic.claude-opus-4-8: anthropic.claude-opus-5: anthropic.claude-sonnet-4-6: anthropic.claude-sonnet-5: global.anthropic.claude-fable-5: global.anthropic.claude-fable-5-1: global.anthropic.claude-opus-4-7: global.anthropic.claude-opus-4-8: global.anthropic.claude-opus-5: global.anthropic.claude-sonnet-4-6: global.anthropic.claude-sonnet-5: us-gov.anthropic.claude-fable-5-1: us-gov.anthropic.claude-opus-4-8: us-gov.anthropic.claude-opus-5: us-gov.anthropic.claude-sonnet-5: us.anthropic.claude-fable-5: us.anthropic.claude-fable-5-1: us.anthropic.claude-opus-4-7: us.anthropic.claude-opus-4-8: us.anthropic.claude-opus-5: us.anthropic.claude-sonnet-4-6: us.anthropic.claude-sonnet-5: --- ...odel_prices_and_context_window_backup.json | 69 +++++++++++++------ model_prices_and_context_window.json | 69 +++++++++++++------ 2 files changed, 94 insertions(+), 44 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 54f19419e47..47cd6faf022 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1312,7 +1312,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-mythos-preview": { "input_cost_per_token": 0, @@ -1365,7 +1366,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1402,7 +1404,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1513,7 +1516,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1551,7 +1555,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1588,7 +1593,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1626,7 +1632,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1663,7 +1670,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, @@ -1701,7 +1709,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1812,7 +1821,8 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1848,7 +1858,8 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1884,7 +1895,8 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -2029,7 +2041,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2066,7 +2079,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2103,7 +2117,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2286,7 +2301,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2323,7 +2339,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2360,7 +2377,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2505,7 +2523,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2539,7 +2558,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2573,7 +2593,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -44977,6 +44998,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45009,6 +45031,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45040,6 +45063,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45089,7 +45113,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 54f19419e47..47cd6faf022 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1312,7 +1312,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-mythos-preview": { "input_cost_per_token": 0, @@ -1365,7 +1366,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1402,7 +1404,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1513,7 +1516,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1551,7 +1555,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1588,7 +1593,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1626,7 +1632,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1663,7 +1670,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, @@ -1701,7 +1709,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1812,7 +1821,8 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1848,7 +1858,8 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1884,7 +1895,8 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -2029,7 +2041,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2066,7 +2079,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2103,7 +2117,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2286,7 +2301,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2323,7 +2339,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2360,7 +2377,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2505,7 +2523,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2539,7 +2558,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2573,7 +2593,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -44977,6 +44998,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45009,6 +45031,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45040,6 +45063,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45089,7 +45113,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, From 8a9a08caf0b4be092df6bc5da5759a0b699edb8e Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 16:31:04 +0000 Subject: [PATCH 03/19] chore(prices): sync prices for 2 providers: 14 models chatgpt-image-latest: input_cost_per_image_token_batches gemini-2.0-flash: input_cost_per_audio_token_batches gemini-2.0-flash-lite: input_cost_per_audio_token_batches gemini-2.5-flash: input_cost_per_audio_token_batches gemini-2.5-flash-lite: input_cost_per_audio_token_batches gemini-3-flash-preview: input_cost_per_audio_token_batches vertex_ai/gemini-3-flash-preview: input_cost_per_audio_token_batches gemini-3.1-flash-lite: input_cost_per_audio_token_batches vertex_ai/gemini-3.1-flash-lite: input_cost_per_audio_token_batches gpt-image-1: input_cost_per_image_token_batches gpt-image-1-mini: input_cost_per_image_token_batches gpt-image-1.5: input_cost_per_image_token_batches gpt-image-1.5-2025-12-16: input_cost_per_image_token_batches gpt-image-2: input_cost_per_image_token_batches --- ...model_prices_and_context_window_backup.json | 18 ++++++++++++++++-- model_prices_and_context_window.json | 18 ++++++++++++++++-- 2 files changed, 32 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 47cd6faf022..e63e2e07216 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -23683,6 +23683,7 @@ "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_character": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, @@ -23762,6 +23763,7 @@ "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_audio_token_batches": 3.75e-08, "input_cost_per_character": 1.875e-08, "input_cost_per_token": 7.5e-08, "input_cost_per_token_batches": 3.75e-08, @@ -23879,6 +23881,7 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, @@ -24261,7 +24264,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -24403,6 +24407,7 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, @@ -25020,6 +25025,7 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, @@ -27387,6 +27393,7 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, @@ -30244,6 +30251,7 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, "output_cost_per_token_batches": 5e-06, @@ -30262,6 +30270,7 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, "output_cost_per_token_batches": 5e-06, @@ -30278,6 +30287,7 @@ "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -33054,6 +33064,7 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, + "input_cost_per_image_token_batches": 5e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", @@ -33069,6 +33080,7 @@ "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-12-01", "input_cost_per_image_token": 2.5e-06, + "input_cost_per_image_token_batches": 1.25e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", @@ -48246,7 +48258,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 }, "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -55302,6 +55315,7 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-01", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 47cd6faf022..e63e2e07216 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -23683,6 +23683,7 @@ "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_character": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, @@ -23762,6 +23763,7 @@ "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_audio_token_batches": 3.75e-08, "input_cost_per_character": 1.875e-08, "input_cost_per_token": 7.5e-08, "input_cost_per_token_batches": 3.75e-08, @@ -23879,6 +23881,7 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, @@ -24261,7 +24264,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -24403,6 +24407,7 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, @@ -25020,6 +25025,7 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, @@ -27387,6 +27393,7 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, @@ -30244,6 +30251,7 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, "output_cost_per_token_batches": 5e-06, @@ -30262,6 +30270,7 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, "output_cost_per_token_batches": 5e-06, @@ -30278,6 +30287,7 @@ "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -33054,6 +33064,7 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, + "input_cost_per_image_token_batches": 5e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", @@ -33069,6 +33080,7 @@ "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-12-01", "input_cost_per_image_token": 2.5e-06, + "input_cost_per_image_token_batches": 1.25e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", @@ -48246,7 +48258,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 }, "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -55302,6 +55315,7 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-01", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", From 68f97321dd1831dce82e9fbff926309057a24f9c Mon Sep 17 00:00:00 2001 From: kerry Date: Tue, 15 Sep 2026 16:45:03 +0000 Subject: [PATCH 04/19] chore(prices): drop source from us-gov rows to match usgov pricing test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 6 +----- model_prices_and_context_window.json | 6 +----- 2 files changed, 2 insertions(+), 10 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e63e2e07216..7a85c332d1a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -45010,7 +45010,6 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45043,7 +45042,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45075,7 +45073,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45125,8 +45122,7 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "prompt_cache_min_tokens": 512 }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e63e2e07216..7a85c332d1a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -45010,7 +45010,6 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45043,7 +45042,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45075,7 +45073,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45125,8 +45122,7 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "prompt_cache_min_tokens": 512 }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, From 1b69cfcf3cbf259c97d8a27bd966f6154889acfe Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 16:51:09 +0000 Subject: [PATCH 05/19] chore(prices): sync AWS Bedrock prices: 4 models us-gov.anthropic.claude-fable-5-1: us-gov.anthropic.claude-opus-4-8: us-gov.anthropic.claude-opus-5: us-gov.anthropic.claude-sonnet-5: --- litellm/model_prices_and_context_window_backup.json | 6 +++++- model_prices_and_context_window.json | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7a85c332d1a..e63e2e07216 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -45010,6 +45010,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45042,6 +45043,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45073,6 +45075,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45122,7 +45125,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7a85c332d1a..e63e2e07216 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -45010,6 +45010,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45042,6 +45043,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45073,6 +45075,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45122,7 +45125,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, From a8dd1394f941cf930107f3f617676ae7c10f2705 Mon Sep 17 00:00:00 2001 From: kerry Date: Tue, 15 Sep 2026 17:04:09 +0000 Subject: [PATCH 06/19] chore(prices): drop source from us-gov rows again Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 6 +----- model_prices_and_context_window.json | 6 +----- 2 files changed, 2 insertions(+), 10 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e63e2e07216..7a85c332d1a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -45010,7 +45010,6 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45043,7 +45042,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45075,7 +45073,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45125,8 +45122,7 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "prompt_cache_min_tokens": 512 }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e63e2e07216..7a85c332d1a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -45010,7 +45010,6 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45043,7 +45042,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45075,7 +45073,6 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45125,8 +45122,7 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "prompt_cache_min_tokens": 512 }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, From 363b7835a3cc17310c5910a0e74784fd839322ab Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 17:06:11 +0000 Subject: [PATCH 07/19] chore(prices): sync AWS Bedrock prices: 4 models us-gov.anthropic.claude-fable-5-1: us-gov.anthropic.claude-opus-4-8: us-gov.anthropic.claude-opus-5: us-gov.anthropic.claude-sonnet-5: --- litellm/model_prices_and_context_window_backup.json | 6 +++++- model_prices_and_context_window.json | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7a85c332d1a..e63e2e07216 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -45010,6 +45010,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45042,6 +45043,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45073,6 +45075,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45122,7 +45125,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7a85c332d1a..e63e2e07216 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -45010,6 +45010,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45042,6 +45043,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45073,6 +45075,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -45122,7 +45125,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, From 1517f1205c23bc2dbed020f8c69210883bb19de2 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 18:36:52 +0000 Subject: [PATCH 08/19] chore(prices): sync Google Gemini prices: 10 models [enrichment failed: Google Gemini, 177 held] gemini/gemini-2.5-computer-use-preview-10-2025: gemini/gemini-2.5-flash: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_flex, cache_read_input_audio_token_cost, input_cost_per_audio_token_batches, cache_read_input_token_cost_priority gemini/gemini-2.5-flash-image: input_cost_per_token_flex, input_cost_per_token_batches, input_cost_per_token_priority gemini/gemini-2.5-flash-lite: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_flex, cache_read_input_audio_token_cost, input_cost_per_audio_token_batches, cache_read_input_token_cost_priority gemini-2.5-flash-preview-tts: gemini/gemini-2.5-flash-preview-tts: gemini/gemini-2.5-pro: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_flex, cache_read_input_token_cost_priority, input_cost_per_token_above_200k_tokens_priority, output_cost_per_token_above_200k_tokens_priority, cache_read_input_token_cost_above_200k_tokens_priority gemini/gemini-2.5-pro-preview-tts: output_cost_per_audio_token, input_cost_per_token_batches gemini/gemini-3-flash-preview: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_flex, cache_read_input_audio_token_cost, input_cost_per_audio_token_batches gemini/gemini-3-pro-image: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_priority, output_cost_per_token_priority --- ...odel_prices_and_context_window_backup.json | 71 +++++++++++++++---- model_prices_and_context_window.json | 71 +++++++++++++++---- 2 files changed, 114 insertions(+), 28 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e63e2e07216..12ee3833ea0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -25899,7 +25899,10 @@ } }, "gemini/gemini-2.5-flash": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_flex": 3e-08, + "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", @@ -25910,7 +25913,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -25944,6 +25947,13 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, "supports_image_size": false }, "gemini/gemini-2.5-flash-image": { @@ -25951,6 +25961,9 @@ "deprecation_date": "2026-10-02", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "gemini", "supports_reasoning": false, "max_input_tokens": 32768, @@ -25962,7 +25975,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26001,6 +26014,8 @@ "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -26012,7 +26027,9 @@ "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26290,7 +26307,10 @@ } }, "gemini/gemini-2.5-flash-lite": { + "cache_read_input_audio_token_cost": 3e-08, "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -26301,7 +26321,7 @@ "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26335,6 +26355,13 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 1.5e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.8e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7.2e-07, "supports_image_size": false }, "gemini/gemini-2.5-flash-lite-preview-09-2025": { @@ -26585,7 +26612,7 @@ "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], @@ -26595,10 +26622,13 @@ "gemini/gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, + "cache_read_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, - "input_cost_per_token_priority": 1.25e-06, - "input_cost_per_token_above_200k_tokens_priority": 2.5e-06, + "input_cost_per_token_priority": 2.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -26606,10 +26636,10 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "output_cost_per_token_priority": 1e-05, - "output_cost_per_token_above_200k_tokens_priority": 1.5e-05, + "output_cost_per_token_priority": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -26640,7 +26670,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-06, @@ -26653,7 +26687,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/computer-use", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -26899,7 +26933,9 @@ "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", @@ -26949,7 +26985,12 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06 }, "gemini/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, @@ -27665,11 +27706,13 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", + "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -55661,7 +55704,7 @@ "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ] diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e63e2e07216..12ee3833ea0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -25899,7 +25899,10 @@ } }, "gemini/gemini-2.5-flash": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_flex": 3e-08, + "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", @@ -25910,7 +25913,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -25944,6 +25947,13 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, "supports_image_size": false }, "gemini/gemini-2.5-flash-image": { @@ -25951,6 +25961,9 @@ "deprecation_date": "2026-10-02", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "gemini", "supports_reasoning": false, "max_input_tokens": 32768, @@ -25962,7 +25975,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26001,6 +26014,8 @@ "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -26012,7 +26027,9 @@ "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26290,7 +26307,10 @@ } }, "gemini/gemini-2.5-flash-lite": { + "cache_read_input_audio_token_cost": 3e-08, "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -26301,7 +26321,7 @@ "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26335,6 +26355,13 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 1.5e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.8e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7.2e-07, "supports_image_size": false }, "gemini/gemini-2.5-flash-lite-preview-09-2025": { @@ -26585,7 +26612,7 @@ "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], @@ -26595,10 +26622,13 @@ "gemini/gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, + "cache_read_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, - "input_cost_per_token_priority": 1.25e-06, - "input_cost_per_token_above_200k_tokens_priority": 2.5e-06, + "input_cost_per_token_priority": 2.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -26606,10 +26636,10 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "output_cost_per_token_priority": 1e-05, - "output_cost_per_token_above_200k_tokens_priority": 1.5e-05, + "output_cost_per_token_priority": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -26640,7 +26670,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-06, @@ -26653,7 +26687,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/computer-use", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -26899,7 +26933,9 @@ "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", @@ -26949,7 +26985,12 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06 }, "gemini/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, @@ -27665,11 +27706,13 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", + "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -55661,7 +55704,7 @@ "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ] From a511c9d45dffdea21e5b974499631ba029a62414 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 18:41:29 +0000 Subject: [PATCH 09/19] chore(prices): sync Google Gemini prices: 7 models [enrichment failed: Google Gemini, 86 held] gemini/gemini-3.1-flash-image: gemini/gemini-3.1-flash-lite: cache_read_input_audio_token_cost, input_cost_per_audio_token_batches gemini/gemini-3.1-flash-lite-image: gemini-3.1-flash-live-preview: gemini/gemini-3.1-flash-live-preview: gemini/gemini-3.1-flash-tts-preview: output_cost_per_audio_token, input_cost_per_token_batches gemini/gemini-3.1-pro-preview: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost_flex --- ...odel_prices_and_context_window_backup.json | 25 ++++++++++++------- model_prices_and_context_window.json | 25 ++++++++++++------- 2 files changed, 32 insertions(+), 18 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 12ee3833ea0..02adbbed736 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -26158,7 +26158,7 @@ "output_cost_per_token_batches": 1.5e-06, "rpm": 1000, "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26243,7 +26243,7 @@ "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "rpm": 1000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26815,6 +26815,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, @@ -26835,7 +26836,7 @@ "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26872,7 +26873,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, @@ -27280,7 +27282,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27315,13 +27317,16 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -55540,7 +55545,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55658,7 +55663,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55684,13 +55689,15 @@ }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "audio_speech", + "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, - "source": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 12ee3833ea0..02adbbed736 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26158,7 +26158,7 @@ "output_cost_per_token_batches": 1.5e-06, "rpm": 1000, "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26243,7 +26243,7 @@ "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "rpm": 1000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26815,6 +26815,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, @@ -26835,7 +26836,7 @@ "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26872,7 +26873,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, @@ -27280,7 +27282,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27315,13 +27317,16 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -55540,7 +55545,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55658,7 +55663,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -55684,13 +55689,15 @@ }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "audio_speech", + "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, - "source": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], From 41caaa301c427088eb836732dc4877b0f00442eb Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 18:46:36 +0000 Subject: [PATCH 10/19] chore(prices): sync prices for 2 providers: 235 models, 59 new [enrichment failed: Google Gemini, 34 held] azure_ai/Codestral-2501: azure_ai/cohere-command-a: azure_ai/deepseek-r1: azure_ai/deepseek-v3: azure_ai/deepseek-v3-0324: azure_ai/deepseek-v3.1: azure_ai/deepseek-v3.2: azure_ai/deepseek-v3.2-speciale: azure_ai/deepseek-v4-flash: azure_ai/DeepSeek-V4-Flash-0731: azure_ai/deepseek-v4-pro: azure_ai/embed-v-4-0: azure_ai/FW-DeepSeek-V3.2: azure_ai/FW-DeepSeek-V4-Pro: azure_ai/FW-GLM-5: azure_ai/FW-GLM-5.1: azure_ai/FW-GLM-5.2: azure_ai/FW-GLM-5.2-Fast: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost azure_ai/FW-Inkling: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost azure_ai/FW-Kimi-K2.5: azure_ai/FW-Kimi-K2.6: azure_ai/FW-Kimi-K2.7-Code: azure_ai/FW-Kimi-K3: azure_ai/FW-MiniMax-M2.5: azure_ai/FW-MiniMax-M3: azure_ai/FW-Nemotron-3-Ultra-NVFP4: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B: azure_ai/gpt-oss-120b: azure_ai/grok-3: azure_ai/global/grok-3: azure_ai/grok-3-mini: azure_ai/global/grok-3-mini: azure_ai/grok-4: azure_ai/grok-4-1-fast-non-reasoning: azure_ai/grok-4-1-fast-reasoning: azure_ai/grok-4-20-non-reasoning: azure_ai/grok-4-20-reasoning: azure_ai/grok-4-fast-non-reasoning: azure_ai/grok-4-fast-reasoning: azure_ai/grok-4.3: azure_ai/grok-4.6: azure_ai/grok-code-fast-1: azure_ai/kimi-k2.5: azure_ai/kimi-k2.6: azure_ai/kimi-k2.7-code: azure_ai/Llama-3.3-70B-Instruct: azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8: input_cost_per_token, output_cost_per_token azure_ai/MAI-DS-R1: azure_ai/MAI-Image-2.5: azure_ai/MAI-Image-2.5-Flash: azure_ai/MAI-Image-2e: azure_ai/MAI-Thinking-1: azure_ai/mistral-large-3: azure_ai/Phi-3-medium-128k-instruct: azure_ai/Phi-3-medium-4k-instruct: azure_ai/Phi-3-mini-128k-instruct: azure_ai/Phi-3-mini-4k-instruct: azure_ai/Phi-3-small-128k-instruct: azure_ai/Phi-3-small-8k-instruct: azure_ai/Phi-3.5-mini-instruct: --- ...odel_prices_and_context_window_backup.json | 1283 ++++++++++++++--- model_prices_and_context_window.json | 1283 ++++++++++++++--- 2 files changed, 2206 insertions(+), 360 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 02adbbed736..1d863977e1e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3144,6 +3144,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3535,6 +3536,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3567,7 +3569,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4172,12 +4174,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4188,13 +4193,17 @@ "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4205,12 +4214,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4351,8 +4362,9 @@ }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -4383,12 +4395,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -4419,18 +4436,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4454,7 +4473,7 @@ }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4462,6 +4481,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4520,12 +4540,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4574,6 +4597,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -4583,12 +4607,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4600,12 +4627,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4631,12 +4661,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4648,12 +4681,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4664,6 +4700,7 @@ "azure/global/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4695,7 +4732,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -4731,7 +4773,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4743,6 +4786,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4774,6 +4818,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5006,8 +5051,10 @@ "azure/gpt-4.1": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5015,6 +5062,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5040,8 +5089,10 @@ "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5049,6 +5100,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5074,8 +5127,10 @@ "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5083,6 +5138,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5108,8 +5165,10 @@ "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5117,6 +5176,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5151,6 +5212,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5184,6 +5246,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5243,12 +5306,15 @@ "azure/gpt-4o-2024-05-13": { "deprecation_date": "2026-10-01", "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5259,12 +5325,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5275,13 +5344,16 @@ "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 2.75e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5468,13 +5540,16 @@ "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5925,6 +6000,9 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { @@ -5963,7 +6041,8 @@ "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -5978,6 +6057,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6012,6 +6092,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6036,13 +6117,19 @@ "azure/gpt-5": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6068,14 +6155,20 @@ }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6109,7 +6202,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6176,6 +6269,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6200,13 +6294,19 @@ "azure/gpt-5-mini": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6232,14 +6332,20 @@ }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6267,12 +6373,15 @@ "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6300,12 +6409,15 @@ "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6332,13 +6444,15 @@ "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", + "output_cost_per_token_batches": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6362,6 +6476,7 @@ "azure/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6393,7 +6508,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6429,7 +6549,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -6441,6 +6562,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6472,6 +6594,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6503,6 +6626,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6527,13 +6651,19 @@ "azure/gpt-5.2": { "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6563,6 +6693,7 @@ "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6570,7 +6701,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6608,6 +6741,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6643,6 +6777,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6675,6 +6810,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6709,6 +6845,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6733,14 +6870,18 @@ }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6764,17 +6905,20 @@ }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6800,17 +6944,20 @@ }, "azure/gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6838,6 +6985,7 @@ "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, @@ -6877,12 +7025,20 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6917,12 +7073,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6957,12 +7119,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", @@ -7003,11 +7171,19 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7043,11 +7219,17 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7083,6 +7265,11 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7092,6 +7279,9 @@ "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7099,11 +7289,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7133,6 +7327,9 @@ "deprecation_date": "2027-09-07", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7140,11 +7337,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7223,33 +7424,42 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7280,17 +7490,23 @@ "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7298,13 +7514,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_priority": 2.4e-05, "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7335,17 +7554,23 @@ "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7353,13 +7578,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7406,6 +7634,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7563,33 +7792,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7645,6 +7875,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7700,6 +7931,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7746,6 +7978,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7866,33 +8099,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7948,6 +8182,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8003,6 +8238,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8034,12 +8270,16 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -8047,13 +8287,15 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8085,9 +8327,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8097,11 +8340,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8133,9 +8378,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8145,11 +8391,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8180,11 +8428,12 @@ "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, @@ -8193,7 +8442,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8223,12 +8472,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8268,12 +8522,15 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8313,7 +8570,10 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -8402,6 +8662,8 @@ "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8439,10 +8701,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", @@ -8481,11 +8752,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8523,10 +8802,16 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", "input_cost_per_token": 2e-07, "litellm_provider": "azure", @@ -8565,6 +8850,11 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-image-1": { @@ -8886,12 +9176,15 @@ "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8900,14 +9193,17 @@ "supports_vision": true }, "azure/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.84e-06, + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8938,6 +9234,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8953,6 +9250,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -8994,12 +9292,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9035,6 +9336,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9078,12 +9380,15 @@ "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -9100,6 +9405,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9131,6 +9437,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9185,12 +9492,15 @@ "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9230,7 +9540,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", @@ -9239,7 +9550,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", @@ -9248,7 +9560,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -9390,12 +9703,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9406,13 +9722,17 @@ "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -9423,12 +9743,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9602,8 +9924,9 @@ }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -9634,12 +9957,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -9670,18 +9998,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9705,7 +10035,7 @@ }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -9713,6 +10043,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9738,12 +10069,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9784,12 +10118,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9822,21 +10159,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 3.1e-07, + "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9882,7 +10223,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -9931,7 +10272,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9946,7 +10287,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9962,7 +10303,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9978,7 +10319,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9993,37 +10334,37 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2-Fast": { - "cache_read_input_token_cost": 2.1e-07, - "input_cost_per_token": 2.1e-06, + "cache_read_input_token_cost": 2.31e-07, + "input_cost_per_token": 2.31e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 7.26e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token": 4.46e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10045,7 +10386,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10068,7 +10409,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10091,7 +10432,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10119,7 +10460,7 @@ "high", "max" ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k3-through-fireworks-ai-on-microsoft-foundry/4540187", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10143,7 +10484,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10158,7 +10499,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10179,7 +10520,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10193,15 +10534,15 @@ "supports_vision": false }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { - "cache_read_input_token_cost": 1.19e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4", + "output_cost_per_token": 2.64e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10220,7 +10561,7 @@ "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_image_token": 4.7e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10234,7 +10575,7 @@ "mode": "image_generation", "output_cost_per_image": 0.0338, "output_cost_per_image_token": 3.3e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10248,7 +10589,7 @@ "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, - "source": "https://aka.ms/mai-image-2e-foundryblog", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations" ] @@ -10262,7 +10603,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10313,19 +10654,19 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 1.41e-06, + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "output_cost_per_token": 1e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -10396,7 +10737,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10408,7 +10749,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10420,7 +10761,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10432,7 +10773,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10444,7 +10785,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10456,7 +10797,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10468,7 +10809,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10480,7 +10821,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10492,7 +10833,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -10504,7 +10845,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -10517,7 +10858,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -10529,20 +10870,20 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { - "input_cost_per_token": 8e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -10553,7 +10894,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -10605,7 +10946,7 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10644,7 +10985,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10709,7 +11050,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10724,7 +11065,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10740,7 +11081,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10752,7 +11093,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3-0324": { @@ -10764,7 +11105,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10777,7 +11118,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.94e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true @@ -10791,7 +11132,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10807,7 +11148,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10824,7 +11165,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10838,7 +11179,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -10857,7 +11198,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10872,7 +11213,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10888,7 +11229,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10903,7 +11244,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10918,7 +11259,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10933,7 +11274,7 @@ "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-grok-4-3-on-microsoft-foundry-latest-generation-agentic-capabilities/4517096", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10951,7 +11292,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-6-comes-to-microsoft-foundry-models-built-for-long-horizon-reasoning-and-/4547578", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10970,7 +11311,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10988,7 +11329,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11004,6 +11345,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11018,7 +11360,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11032,7 +11374,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11046,7 +11388,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -11061,7 +11403,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11096,7 +11438,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -11113,7 +11455,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -11183,7 +11525,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -61814,7 +62156,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -66133,5 +66475,586 @@ "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" + }, + "azure/eu/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-6-astra": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-2025-04-16": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "azure/us/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 02adbbed736..1d863977e1e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3144,6 +3144,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3535,6 +3536,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3567,7 +3569,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4172,12 +4174,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4188,13 +4193,17 @@ "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4205,12 +4214,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4351,8 +4362,9 @@ }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -4383,12 +4395,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -4419,18 +4436,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4454,7 +4473,7 @@ }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4462,6 +4481,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4520,12 +4540,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4574,6 +4597,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -4583,12 +4607,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4600,12 +4627,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4631,12 +4661,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4648,12 +4681,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4664,6 +4700,7 @@ "azure/global/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4695,7 +4732,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -4731,7 +4773,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4743,6 +4786,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4774,6 +4818,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5006,8 +5051,10 @@ "azure/gpt-4.1": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5015,6 +5062,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5040,8 +5089,10 @@ "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5049,6 +5100,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5074,8 +5127,10 @@ "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5083,6 +5138,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5108,8 +5165,10 @@ "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5117,6 +5176,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5151,6 +5212,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5184,6 +5246,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5243,12 +5306,15 @@ "azure/gpt-4o-2024-05-13": { "deprecation_date": "2026-10-01", "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5259,12 +5325,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5275,13 +5344,16 @@ "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 2.75e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5468,13 +5540,16 @@ "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5925,6 +6000,9 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { @@ -5963,7 +6041,8 @@ "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -5978,6 +6057,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6012,6 +6092,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6036,13 +6117,19 @@ "azure/gpt-5": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6068,14 +6155,20 @@ }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6109,7 +6202,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6176,6 +6269,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6200,13 +6294,19 @@ "azure/gpt-5-mini": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6232,14 +6332,20 @@ }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6267,12 +6373,15 @@ "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6300,12 +6409,15 @@ "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6332,13 +6444,15 @@ "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", + "output_cost_per_token_batches": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6362,6 +6476,7 @@ "azure/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6393,7 +6508,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6429,7 +6549,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -6441,6 +6562,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6472,6 +6594,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6503,6 +6626,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6527,13 +6651,19 @@ "azure/gpt-5.2": { "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6563,6 +6693,7 @@ "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6570,7 +6701,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6608,6 +6741,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6643,6 +6777,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6675,6 +6810,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6709,6 +6845,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6733,14 +6870,18 @@ }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6764,17 +6905,20 @@ }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6800,17 +6944,20 @@ }, "azure/gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6838,6 +6985,7 @@ "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, @@ -6877,12 +7025,20 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6917,12 +7073,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6957,12 +7119,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", @@ -7003,11 +7171,19 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7043,11 +7219,17 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7083,6 +7265,11 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7092,6 +7279,9 @@ "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7099,11 +7289,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7133,6 +7327,9 @@ "deprecation_date": "2027-09-07", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7140,11 +7337,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7223,33 +7424,42 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7280,17 +7490,23 @@ "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7298,13 +7514,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_priority": 2.4e-05, "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7335,17 +7554,23 @@ "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7353,13 +7578,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7406,6 +7634,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7563,33 +7792,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7645,6 +7875,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7700,6 +7931,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7746,6 +7978,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7866,33 +8099,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7948,6 +8182,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8003,6 +8238,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8034,12 +8270,16 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -8047,13 +8287,15 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8085,9 +8327,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8097,11 +8340,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "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 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8133,9 +8378,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8145,11 +8391,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8180,11 +8428,12 @@ "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, @@ -8193,7 +8442,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "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, @@ -8223,12 +8472,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8268,12 +8522,15 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8313,7 +8570,10 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -8402,6 +8662,8 @@ "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8439,10 +8701,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", @@ -8481,11 +8752,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8523,10 +8802,16 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", "input_cost_per_token": 2e-07, "litellm_provider": "azure", @@ -8565,6 +8850,11 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-image-1": { @@ -8886,12 +9176,15 @@ "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8900,14 +9193,17 @@ "supports_vision": true }, "azure/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.84e-06, + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8938,6 +9234,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8953,6 +9250,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -8994,12 +9292,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9035,6 +9336,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9078,12 +9380,15 @@ "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -9100,6 +9405,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9131,6 +9437,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9185,12 +9492,15 @@ "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9230,7 +9540,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", @@ -9239,7 +9550,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", @@ -9248,7 +9560,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -9390,12 +9703,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9406,13 +9722,17 @@ "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -9423,12 +9743,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9602,8 +9924,9 @@ }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -9634,12 +9957,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -9670,18 +9998,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9705,7 +10035,7 @@ }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -9713,6 +10043,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9738,12 +10069,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9784,12 +10118,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9822,21 +10159,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 3.1e-07, + "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9882,7 +10223,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -9931,7 +10272,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9946,7 +10287,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9962,7 +10303,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9978,7 +10319,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9993,37 +10334,37 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2-Fast": { - "cache_read_input_token_cost": 2.1e-07, - "input_cost_per_token": 2.1e-06, + "cache_read_input_token_cost": 2.31e-07, + "input_cost_per_token": 2.31e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 7.26e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token": 4.46e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10045,7 +10386,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10068,7 +10409,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10091,7 +10432,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10119,7 +10460,7 @@ "high", "max" ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k3-through-fireworks-ai-on-microsoft-foundry/4540187", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10143,7 +10484,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10158,7 +10499,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10179,7 +10520,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10193,15 +10534,15 @@ "supports_vision": false }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { - "cache_read_input_token_cost": 1.19e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4", + "output_cost_per_token": 2.64e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10220,7 +10561,7 @@ "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_image_token": 4.7e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10234,7 +10575,7 @@ "mode": "image_generation", "output_cost_per_image": 0.0338, "output_cost_per_image_token": 3.3e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10248,7 +10589,7 @@ "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, - "source": "https://aka.ms/mai-image-2e-foundryblog", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations" ] @@ -10262,7 +10603,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10313,19 +10654,19 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 1.41e-06, + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "output_cost_per_token": 1e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -10396,7 +10737,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10408,7 +10749,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10420,7 +10761,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10432,7 +10773,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10444,7 +10785,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10456,7 +10797,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10468,7 +10809,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10480,7 +10821,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10492,7 +10833,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -10504,7 +10845,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -10517,7 +10858,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -10529,20 +10870,20 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { - "input_cost_per_token": 8e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -10553,7 +10894,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -10605,7 +10946,7 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10644,7 +10985,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10709,7 +11050,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10724,7 +11065,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10740,7 +11081,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10752,7 +11093,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3-0324": { @@ -10764,7 +11105,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10777,7 +11118,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.94e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true @@ -10791,7 +11132,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10807,7 +11148,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10824,7 +11165,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10838,7 +11179,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -10857,7 +11198,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10872,7 +11213,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10888,7 +11229,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10903,7 +11244,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10918,7 +11259,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10933,7 +11274,7 @@ "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-grok-4-3-on-microsoft-foundry-latest-generation-agentic-capabilities/4517096", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10951,7 +11292,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-6-comes-to-microsoft-foundry-models-built-for-long-horizon-reasoning-and-/4547578", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10970,7 +11311,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10988,7 +11329,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11004,6 +11345,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11018,7 +11360,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11032,7 +11374,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11046,7 +11388,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -11061,7 +11403,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11096,7 +11438,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -11113,7 +11455,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -11183,7 +11525,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -61814,7 +62156,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -66133,5 +66475,586 @@ "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" + }, + "azure/eu/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-6-astra": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-2025-04-16": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "azure/us/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" } } From 9f4fbcfe4142de1c5752dd61e7742482331612ad Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 18:51:21 +0000 Subject: [PATCH 11/19] chore(prices): sync Azure prices: 14 models [enrichment failed: Google Gemini, 34 held] azure/eu/gpt-5-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/eu/gpt-5-mini-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/eu/gpt-5-nano-2025-08-07: input_cost_per_token_batches, output_cost_per_token_batches azure/eu/o1-mini-2024-09-12: azure/eu/o1-preview-2024-09-12: azure/o1-mini-2024-09-12: input_cost_per_token_batches, output_cost_per_token_batches azure/us/gpt-4.1-2025-04-14: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-4.1-mini-2025-04-14: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-4.1-nano-2025-04-14: cache_read_input_token_cost, input_cost_per_token_batches azure/us/gpt-5-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-5-mini-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-5-nano-2025-08-07: input_cost_per_token_batches, output_cost_per_token_batches azure/us/o1-mini-2024-09-12: azure/us/o1-preview-2024-09-12: --- ...odel_prices_and_context_window_backup.json | 50 ++++++++++++++++++- model_prices_and_context_window.json | 50 ++++++++++++++++++- 2 files changed, 96 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1d863977e1e..372ce19e740 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4296,14 +4296,20 @@ }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4329,14 +4335,20 @@ }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4507,12 +4519,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4566,6 +4581,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4580,6 +4596,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9213,12 +9230,15 @@ "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9601,8 +9621,10 @@ "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9610,6 +9632,8 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9635,8 +9659,10 @@ "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9644,6 +9670,8 @@ "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9668,9 +9696,9 @@ }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9678,6 +9706,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9825,14 +9854,20 @@ }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9858,14 +9893,20 @@ }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9893,12 +9934,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10095,6 +10139,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10109,6 +10154,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1d863977e1e..372ce19e740 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4296,14 +4296,20 @@ }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4329,14 +4335,20 @@ }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4507,12 +4519,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4566,6 +4581,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4580,6 +4596,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9213,12 +9230,15 @@ "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9601,8 +9621,10 @@ "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9610,6 +9632,8 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9635,8 +9659,10 @@ "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9644,6 +9670,8 @@ "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9668,9 +9696,9 @@ }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9678,6 +9706,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9825,14 +9854,20 @@ }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9858,14 +9893,20 @@ }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9893,12 +9934,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10095,6 +10139,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10109,6 +10154,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, From 083ecb3c0b6a732c642bf16db80be87357e9cd41 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 23:31:18 +0000 Subject: [PATCH 12/19] chore(prices): sync prices for 3 providers: 26 models, 26 deprecated [enrichment failed: Google Gemini, sync failed: AWS Bedrock, 34 held] fireworks_ai/accounts/fireworks/models/deepseek-v4-pro: deprecation_date fireworks_ai/deepseek-v4-pro: deprecation_date fireworks_ai/accounts/fireworks/models/minimax-m2p7: deprecation_date fireworks_ai/minimax-m2p7: deprecation_date together_ai/deepseek-ai/deepseek-coder-33b-instruct: deprecation_date together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B: deprecation_date together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B: deprecation_date together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B: deprecation_date together_ai/google/gemma-2-27b-it: deprecation_date vertex_ai/imagegeneration@006: deprecation_date vertex_ai/imagen-3.0-capability-001: deprecation_date vertex_ai/imagen-3.0-fast-generate-001: deprecation_date vertex_ai/imagen-3.0-generate-001: deprecation_date vertex_ai/imagen-3.0-generate-002: deprecation_date vertex_ai/imagen-4.0-fast-generate-001: deprecation_date vertex_ai/imagen-4.0-generate-001: deprecation_date vertex_ai/imagen-4.0-ultra-generate-001: deprecation_date together_ai/meta-llama/Llama-3-8b-chat-hf: deprecation_date together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo: deprecation_date together_ai/meta-llama/Meta-Llama-3-8B-Instruct: deprecation_date together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO: deprecation_date together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF: deprecation_date together_ai/Qwen/Qwen2-72B-Instruct: deprecation_date together_ai/Qwen/Qwen2-VL-72B-Instruct: deprecation_date together_ai/Qwen/Qwen2.5-Coder-32B-Instruct: deprecation_date together_ai/Qwen/Qwen2.5-VL-72B-Instruct: deprecation_date --- ...odel_prices_and_context_window_backup.json | 27 ++++++++++++++++++- model_prices_and_context_window.json | 27 ++++++++++++++++++- 2 files changed, 52 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 372ce19e740..000615bea11 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -22839,6 +22839,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { "cache_read_input_token_cost": 6e-07, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 1.2e-06, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -23226,6 +23227,7 @@ "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -23332,6 +23334,7 @@ "fireworks_ai/deepseek-v4-pro": { "cache_read_input_token_cost": 6e-07, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 1.2e-06, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -23550,6 +23553,7 @@ "fireworks_ai/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -48772,49 +48776,56 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/imagegeneration@006": { + "deprecation_date": "2025-09-24", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-fast-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-generate-002": { - "deprecation_date": "2025-11-10", + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-capability-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" }, "vertex_ai/imagen-4.0-fast-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-4.0-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-4.0-ultra-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.06, @@ -66280,6 +66291,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66287,6 +66299,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66294,6 +66307,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66301,6 +66315,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66394,6 +66409,7 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66418,6 +66434,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66446,6 +66463,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66453,6 +66471,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66460,6 +66479,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66467,6 +66487,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66481,6 +66502,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66488,6 +66510,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66509,6 +66532,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66516,6 +66540,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "mode": "chat", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 372ce19e740..000615bea11 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -22839,6 +22839,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { "cache_read_input_token_cost": 6e-07, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 1.2e-06, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -23226,6 +23227,7 @@ "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -23332,6 +23334,7 @@ "fireworks_ai/deepseek-v4-pro": { "cache_read_input_token_cost": 6e-07, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 1.2e-06, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -23550,6 +23553,7 @@ "fireworks_ai/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", @@ -48772,49 +48776,56 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/imagegeneration@006": { + "deprecation_date": "2025-09-24", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-fast-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-generate-002": { - "deprecation_date": "2025-11-10", + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-3.0-capability-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" }, "vertex_ai/imagen-4.0-fast-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-4.0-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/imagen-4.0-ultra-generate-001": { + "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.06, @@ -66280,6 +66291,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66287,6 +66299,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66294,6 +66307,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66301,6 +66315,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66394,6 +66409,7 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66418,6 +66434,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66446,6 +66463,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66453,6 +66471,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66460,6 +66479,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66467,6 +66487,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66481,6 +66502,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66488,6 +66510,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66509,6 +66532,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66516,6 +66540,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "mode": "chat", From c5a388a94cfec0fd06793ddec7012243c0f270bc Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 01:46:17 +0000 Subject: [PATCH 13/19] chore(prices): sync Google Gemini prices: 1 model [enrichment failed: Google Gemini, sync failed: AWS Bedrock, 6 held] gemini/gemini-3.1-pro-preview-customtools: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost_flex --- litellm/model_prices_and_context_window_backup.json | 7 +++++-- model_prices_and_context_window.json | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 5fb4aad96d2..f6589351cd4 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27738,7 +27738,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27773,13 +27773,16 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 5fb4aad96d2..f6589351cd4 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -27738,7 +27738,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27773,13 +27773,16 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, From 641dcd5f8f951b2da2bfb90c0557c02ff0811b86 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 03:46:34 +0000 Subject: [PATCH 14/19] chore(prices): sync Google Gemini prices: 1 model gemini/gemini-robotics-er-2-preview: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_batches, output_cost_per_token_batches --- litellm/model_prices_and_context_window_backup.json | 10 ++++++---- model_prices_and_context_window.json | 10 ++++++---- 2 files changed, 12 insertions(+), 8 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f6589351cd4..ea219137c15 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -25893,22 +25893,24 @@ } }, "gemini/gemini-robotics-er-2-preview": { - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f6589351cd4..ea219137c15 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -25893,22 +25893,24 @@ } }, "gemini/gemini-robotics-er-2-preview": { - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", From 0443605c40a4aafdc4fd3c8f8f9ecb5e9cbdba03 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 13:16:12 +0000 Subject: [PATCH 15/19] chore(prices): sync Together AI prices: 4 models, 4 deprecated together_ai/google/gemma-4-31B-it: deprecation_date together_ai/intfloat/multilingual-e5-large-instruct: deprecation_date together_ai/openai/gpt-oss-20b: deprecation_date together_ai/thinkingmachines/Inkling-Small: deprecation_date --- litellm/model_prices_and_context_window_backup.json | 8 ++++---- model_prices_and_context_window.json | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index ea219137c15..690e4220f98 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -44586,7 +44586,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -44879,7 +44879,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -44894,7 +44894,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -45007,7 +45007,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index ea219137c15..690e4220f98 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -44586,7 +44586,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -44879,7 +44879,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -44894,7 +44894,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -45007,7 +45007,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", From 809685603ae24723f3cb3041ee8090c04af02557 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 16:26:23 +0000 Subject: [PATCH 16/19] chore(prices): sync Azure prices: 247 models azure_ai/Codestral-2501: azure_ai/cohere-command-a: azure_ai/deepseek-r1: azure_ai/deepseek-v3: azure_ai/deepseek-v3-0324: azure_ai/deepseek-v3.1: azure_ai/deepseek-v3.2: azure_ai/deepseek-v3.2-speciale: azure_ai/deepseek-v4-flash: azure_ai/DeepSeek-V4-Flash-0731: azure_ai/deepseek-v4-pro: azure_ai/embed-v-4-0: azure_ai/FW-DeepSeek-V3.2: azure_ai/FW-DeepSeek-V4-Pro: azure_ai/FW-GLM-5: azure_ai/FW-GLM-5.1: azure_ai/FW-GLM-5.2: azure_ai/FW-GLM-5.2-Fast: azure_ai/FW-Inkling: azure_ai/FW-Kimi-K2.5: azure_ai/FW-Kimi-K2.6: azure_ai/FW-Kimi-K2.7-Code: azure_ai/FW-Kimi-K3: azure_ai/FW-MiniMax-M2.5: azure_ai/FW-MiniMax-M3: azure_ai/FW-Nemotron-3-Ultra-NVFP4: azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B: azure_ai/gpt-oss-120b: azure_ai/grok-3: azure_ai/global/grok-3: azure_ai/grok-3-mini: azure_ai/global/grok-3-mini: azure_ai/grok-4: azure_ai/grok-4-1-fast-non-reasoning: azure_ai/grok-4-1-fast-reasoning: azure_ai/grok-4-20-non-reasoning: azure_ai/grok-4-20-reasoning: azure_ai/grok-4-fast-non-reasoning: azure_ai/grok-4-fast-reasoning: azure_ai/grok-4.3: azure_ai/grok-4.6: azure_ai/grok-code-fast-1: azure_ai/kimi-k2.5: azure_ai/kimi-k2.6: azure_ai/kimi-k2.7-code: azure_ai/Llama-3.3-70B-Instruct: azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8: azure_ai/MAI-DS-R1: azure_ai/MAI-Image-2.5: azure_ai/MAI-Image-2.5-Flash: azure_ai/MAI-Image-2e: azure_ai/MAI-Thinking-1: azure_ai/mistral-large-3: azure_ai/Phi-3-medium-128k-instruct: azure_ai/Phi-3-medium-4k-instruct: azure_ai/Phi-3-mini-128k-instruct: azure_ai/Phi-3-mini-4k-instruct: azure_ai/Phi-3-small-128k-instruct: azure_ai/Phi-3-small-8k-instruct: azure_ai/Phi-3.5-mini-instruct: --- ...odel_prices_and_context_window_backup.json | 494 +++++++++--------- model_prices_and_context_window.json | 494 +++++++++--------- 2 files changed, 494 insertions(+), 494 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 690e4220f98..27344af1991 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3144,7 +3144,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3536,7 +3536,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3569,7 +3569,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4182,7 +4182,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4203,7 +4203,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4221,7 +4221,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4309,7 +4309,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4348,7 +4348,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4412,7 +4412,7 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, @@ -4449,7 +4449,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4461,7 +4461,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4493,7 +4493,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4527,7 +4527,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4563,7 +4563,7 @@ "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4581,7 +4581,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4596,7 +4596,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4614,7 +4614,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -4632,7 +4632,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4652,7 +4652,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4686,7 +4686,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4706,7 +4706,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4754,7 +4754,7 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -4791,7 +4791,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4803,7 +4803,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4835,7 +4835,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5080,7 +5080,7 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5118,7 +5118,7 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5156,7 +5156,7 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5194,7 +5194,7 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5229,7 +5229,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5263,7 +5263,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5331,7 +5331,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5350,7 +5350,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5370,7 +5370,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5566,7 +5566,7 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -6019,7 +6019,7 @@ "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { @@ -6059,7 +6059,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -6074,7 +6074,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6109,7 +6109,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6146,7 +6146,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6185,7 +6185,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6219,7 +6219,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6286,7 +6286,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6323,7 +6323,7 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6362,7 +6362,7 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6398,7 +6398,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6434,7 +6434,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6469,7 +6469,7 @@ "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6530,7 +6530,7 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6567,7 +6567,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -6579,7 +6579,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6611,7 +6611,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6643,7 +6643,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6680,7 +6680,7 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6720,7 +6720,7 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6758,7 +6758,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6794,7 +6794,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6827,7 +6827,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6862,7 +6862,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6898,7 +6898,7 @@ "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6935,7 +6935,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6974,7 +6974,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7048,7 +7048,7 @@ "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_flex": 7.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7094,7 +7094,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7140,7 +7140,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7194,7 +7194,7 @@ "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_flex": 7.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7240,7 +7240,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7286,7 +7286,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7314,7 +7314,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7362,7 +7362,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7476,7 +7476,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7540,7 +7540,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7604,7 +7604,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7651,7 +7651,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7836,7 +7836,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7892,7 +7892,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7948,7 +7948,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7995,7 +7995,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8143,7 +8143,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8199,7 +8199,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8255,7 +8255,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8312,7 +8312,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8363,7 +8363,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8414,7 +8414,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8494,7 +8494,7 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "output_cost_per_token_batches": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -8542,7 +8542,7 @@ "deprecation_date": "2027-10-26", "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.65e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -8590,7 +8590,7 @@ "deprecation_date": "2027-10-26", "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.65e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -8724,7 +8724,7 @@ "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { @@ -8775,7 +8775,7 @@ "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano": { @@ -8823,7 +8823,7 @@ "input_cost_per_token_flex": 1e-07, "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { @@ -8871,7 +8871,7 @@ "input_cost_per_token_flex": 1e-07, "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-image-1": { @@ -9201,7 +9201,7 @@ "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9220,7 +9220,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9238,7 +9238,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9254,7 +9254,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9270,7 +9270,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -9320,7 +9320,7 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9356,7 +9356,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9408,7 +9408,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -9425,7 +9425,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9457,7 +9457,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9520,7 +9520,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9561,7 +9561,7 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", @@ -9571,7 +9571,7 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", @@ -9581,7 +9581,7 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -9633,7 +9633,7 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9671,7 +9671,7 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9706,7 +9706,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9740,7 +9740,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9761,7 +9761,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -9779,7 +9779,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9867,7 +9867,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9906,7 +9906,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9942,7 +9942,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10006,7 +10006,7 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, @@ -10043,7 +10043,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -10055,7 +10055,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -10087,7 +10087,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -10121,7 +10121,7 @@ "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10139,7 +10139,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10154,7 +10154,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10172,7 +10172,7 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10205,7 +10205,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10223,7 +10223,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -10269,7 +10269,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10318,7 +10318,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10333,7 +10333,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10349,7 +10349,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10365,7 +10365,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10380,7 +10380,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10395,7 +10395,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10410,7 +10410,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10432,7 +10432,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10455,7 +10455,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10478,7 +10478,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10506,7 +10506,7 @@ "high", "max" ], - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10530,7 +10530,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10545,7 +10545,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10566,7 +10566,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10588,7 +10588,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10607,7 +10607,7 @@ "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_image_token": 4.7e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10621,7 +10621,7 @@ "mode": "image_generation", "output_cost_per_image": 0.0338, "output_cost_per_image_token": 3.3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10635,7 +10635,7 @@ "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations" ] @@ -10649,7 +10649,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10700,7 +10700,7 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10712,7 +10712,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -10783,7 +10783,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10795,7 +10795,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10807,7 +10807,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10819,7 +10819,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10831,7 +10831,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10843,7 +10843,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10855,7 +10855,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10867,7 +10867,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10879,7 +10879,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -10891,7 +10891,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -10904,7 +10904,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -10916,7 +10916,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true @@ -10929,7 +10929,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -10940,7 +10940,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -10992,7 +10992,7 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -11031,7 +11031,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -11096,7 +11096,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -11111,7 +11111,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -11127,7 +11127,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -11139,7 +11139,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3-0324": { @@ -11151,7 +11151,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -11164,7 +11164,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.94e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11178,7 +11178,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11194,7 +11194,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11211,7 +11211,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11225,7 +11225,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -11244,7 +11244,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -11259,7 +11259,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -11275,7 +11275,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -11290,7 +11290,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -11305,7 +11305,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11320,7 +11320,7 @@ "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11338,7 +11338,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11357,7 +11357,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11375,7 +11375,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11391,7 +11391,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11406,7 +11406,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11420,7 +11420,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11434,7 +11434,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -11449,7 +11449,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11484,7 +11484,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -11501,7 +11501,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -11571,7 +11571,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -62237,7 +62237,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -66577,14 +66577,14 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/computer-use-preview": { "input_cost_per_token": 3.3e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.32e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1": { "cache_read_input_token_cost": 5.5e-07, @@ -66597,7 +66597,7 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { "cache_read_input_token_cost": 1.1e-07, @@ -66610,7 +66610,7 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { "cache_read_input_token_cost": 2.8e-08, @@ -66620,7 +66620,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4o-2024-05-13": { "input_cost_per_token": 5.5e-06, @@ -66629,7 +66629,7 @@ "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5": { "cache_read_input_token_cost": 1.375e-07, @@ -66642,7 +66642,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { "cache_read_input_token_cost": 1.38e-07, @@ -66650,7 +66650,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-mini": { "cache_read_input_token_cost": 2.75e-08, @@ -66663,7 +66663,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { "cache_read_input_token_cost": 5.5e-09, @@ -66673,7 +66673,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { "input_cost_per_token": 1.65e-05, @@ -66682,7 +66682,7 @@ "mode": "chat", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.375e-07, @@ -66690,7 +66690,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2": { "cache_read_input_token_cost": 1.925e-07, @@ -66703,7 +66703,7 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -66711,7 +66711,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -66719,7 +66719,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-pro": { "input_cost_per_token": 2.31e-05, @@ -66728,7 +66728,7 @@ "mode": "chat", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -66736,7 +66736,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -66747,7 +66747,7 @@ "mode": "chat", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { "cache_read_input_token_cost": 8.25e-08, @@ -66760,7 +66760,7 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { "cache_read_input_token_cost": 2.2e-08, @@ -66770,7 +66770,7 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { "input_cost_per_token": 3.3e-05, @@ -66781,7 +66781,7 @@ "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_batches": 9.9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-6-astra": { "cache_creation_input_token_cost": 1.375e-05, @@ -66794,7 +66794,7 @@ "mode": "chat", "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o1-mini": { "cache_read_input_token_cost": 6.05e-07, @@ -66804,7 +66804,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o1-preview": { "cache_read_input_token_cost": 8.25e-06, @@ -66812,7 +66812,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { "cache_read_input_token_cost": 5.5e-07, @@ -66822,7 +66822,7 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { "cache_read_input_token_cost": 2.75e-06, @@ -66830,7 +66830,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, @@ -66840,25 +66840,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-small": { "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-ada-002": { "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "gemini/gemini-3.8-live": { "input_cost_per_audio_token": 3e-06, @@ -66902,14 +66902,14 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/computer-use-preview": { "input_cost_per_token": 3.3e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.32e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1": { "cache_read_input_token_cost": 5.5e-07, @@ -66922,7 +66922,7 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { "cache_read_input_token_cost": 1.1e-07, @@ -66935,7 +66935,7 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { "cache_read_input_token_cost": 2.8e-08, @@ -66945,7 +66945,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4o-2024-05-13": { "input_cost_per_token": 5.5e-06, @@ -66954,7 +66954,7 @@ "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5": { "cache_read_input_token_cost": 1.375e-07, @@ -66967,7 +66967,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { "cache_read_input_token_cost": 1.38e-07, @@ -66975,7 +66975,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini": { "cache_read_input_token_cost": 2.75e-08, @@ -66988,7 +66988,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { "cache_read_input_token_cost": 5.5e-09, @@ -66998,7 +66998,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { "input_cost_per_token": 1.65e-05, @@ -67007,7 +67007,7 @@ "mode": "chat", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.375e-07, @@ -67015,7 +67015,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2": { "cache_read_input_token_cost": 1.925e-07, @@ -67028,7 +67028,7 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -67036,7 +67036,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -67044,7 +67044,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-pro": { "input_cost_per_token": 2.31e-05, @@ -67053,7 +67053,7 @@ "mode": "chat", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -67061,7 +67061,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -67072,7 +67072,7 @@ "mode": "chat", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { "cache_read_input_token_cost": 8.25e-08, @@ -67085,7 +67085,7 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { "cache_read_input_token_cost": 2.2e-08, @@ -67095,7 +67095,7 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { "input_cost_per_token": 3.3e-05, @@ -67106,7 +67106,7 @@ "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_batches": 9.9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-mini": { "cache_read_input_token_cost": 6.05e-07, @@ -67116,7 +67116,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-preview": { "cache_read_input_token_cost": 8.25e-06, @@ -67124,7 +67124,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o3-deep-research": { "cache_read_input_token_cost": 2.75e-06, @@ -67132,25 +67132,25 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-large": { "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-small": { "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-ada-002": { "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "aihubmix/agnes-2.5-flash": { "input_cost_per_token": 3e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 690e4220f98..27344af1991 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3144,7 +3144,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3536,7 +3536,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3569,7 +3569,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4182,7 +4182,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4203,7 +4203,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4221,7 +4221,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4309,7 +4309,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4348,7 +4348,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4412,7 +4412,7 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, @@ -4449,7 +4449,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4461,7 +4461,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4493,7 +4493,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4527,7 +4527,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4563,7 +4563,7 @@ "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4581,7 +4581,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4596,7 +4596,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4614,7 +4614,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -4632,7 +4632,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4652,7 +4652,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4686,7 +4686,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4706,7 +4706,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4754,7 +4754,7 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -4791,7 +4791,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4803,7 +4803,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4835,7 +4835,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5080,7 +5080,7 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5118,7 +5118,7 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5156,7 +5156,7 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5194,7 +5194,7 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5229,7 +5229,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5263,7 +5263,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5331,7 +5331,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5350,7 +5350,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5370,7 +5370,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5566,7 +5566,7 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -6019,7 +6019,7 @@ "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { @@ -6059,7 +6059,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -6074,7 +6074,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6109,7 +6109,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6146,7 +6146,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6185,7 +6185,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6219,7 +6219,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6286,7 +6286,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6323,7 +6323,7 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6362,7 +6362,7 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6398,7 +6398,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6434,7 +6434,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6469,7 +6469,7 @@ "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6530,7 +6530,7 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6567,7 +6567,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -6579,7 +6579,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6611,7 +6611,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6643,7 +6643,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6680,7 +6680,7 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6720,7 +6720,7 @@ "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6758,7 +6758,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6794,7 +6794,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6827,7 +6827,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6862,7 +6862,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6898,7 +6898,7 @@ "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6935,7 +6935,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6974,7 +6974,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7048,7 +7048,7 @@ "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_flex": 7.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7094,7 +7094,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7140,7 +7140,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7194,7 +7194,7 @@ "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_flex": 7.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7240,7 +7240,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7286,7 +7286,7 @@ "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7314,7 +7314,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7362,7 +7362,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7476,7 +7476,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7540,7 +7540,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7604,7 +7604,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7651,7 +7651,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7836,7 +7836,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7892,7 +7892,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7948,7 +7948,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7995,7 +7995,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8143,7 +8143,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8199,7 +8199,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8255,7 +8255,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8312,7 +8312,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8363,7 +8363,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8414,7 +8414,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8494,7 +8494,7 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "output_cost_per_token_batches": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -8542,7 +8542,7 @@ "deprecation_date": "2027-10-26", "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.65e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -8590,7 +8590,7 @@ "deprecation_date": "2027-10-26", "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.65e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -8724,7 +8724,7 @@ "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { @@ -8775,7 +8775,7 @@ "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano": { @@ -8823,7 +8823,7 @@ "input_cost_per_token_flex": 1e-07, "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { @@ -8871,7 +8871,7 @@ "input_cost_per_token_flex": 1e-07, "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-image-1": { @@ -9201,7 +9201,7 @@ "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9220,7 +9220,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9238,7 +9238,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9254,7 +9254,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9270,7 +9270,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -9320,7 +9320,7 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9356,7 +9356,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9408,7 +9408,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -9425,7 +9425,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9457,7 +9457,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9520,7 +9520,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9561,7 +9561,7 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", @@ -9571,7 +9571,7 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", @@ -9581,7 +9581,7 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -9633,7 +9633,7 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9671,7 +9671,7 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9706,7 +9706,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9740,7 +9740,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9761,7 +9761,7 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -9779,7 +9779,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9867,7 +9867,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9906,7 +9906,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9942,7 +9942,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10006,7 +10006,7 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, @@ -10043,7 +10043,7 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -10055,7 +10055,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -10087,7 +10087,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -10121,7 +10121,7 @@ "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10139,7 +10139,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10154,7 +10154,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10172,7 +10172,7 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10205,7 +10205,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10223,7 +10223,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -10269,7 +10269,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10318,7 +10318,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10333,7 +10333,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10349,7 +10349,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10365,7 +10365,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10380,7 +10380,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10395,7 +10395,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10410,7 +10410,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10432,7 +10432,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10455,7 +10455,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10478,7 +10478,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10506,7 +10506,7 @@ "high", "max" ], - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10530,7 +10530,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10545,7 +10545,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10566,7 +10566,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10588,7 +10588,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10607,7 +10607,7 @@ "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_image_token": 4.7e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10621,7 +10621,7 @@ "mode": "image_generation", "output_cost_per_image": 0.0338, "output_cost_per_image_token": 3.3e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10635,7 +10635,7 @@ "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations" ] @@ -10649,7 +10649,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10700,7 +10700,7 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10712,7 +10712,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -10783,7 +10783,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10795,7 +10795,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10807,7 +10807,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10819,7 +10819,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10831,7 +10831,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10843,7 +10843,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10855,7 +10855,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10867,7 +10867,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10879,7 +10879,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -10891,7 +10891,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -10904,7 +10904,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -10916,7 +10916,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true @@ -10929,7 +10929,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -10940,7 +10940,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -10992,7 +10992,7 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -11031,7 +11031,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -11096,7 +11096,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -11111,7 +11111,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -11127,7 +11127,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -11139,7 +11139,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3-0324": { @@ -11151,7 +11151,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -11164,7 +11164,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.94e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11178,7 +11178,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11194,7 +11194,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11211,7 +11211,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11225,7 +11225,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -11244,7 +11244,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -11259,7 +11259,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -11275,7 +11275,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -11290,7 +11290,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -11305,7 +11305,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11320,7 +11320,7 @@ "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11338,7 +11338,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11357,7 +11357,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11375,7 +11375,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11391,7 +11391,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11406,7 +11406,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11420,7 +11420,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11434,7 +11434,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -11449,7 +11449,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11484,7 +11484,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -11501,7 +11501,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -11571,7 +11571,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -62237,7 +62237,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -66577,14 +66577,14 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/computer-use-preview": { "input_cost_per_token": 3.3e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.32e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1": { "cache_read_input_token_cost": 5.5e-07, @@ -66597,7 +66597,7 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { "cache_read_input_token_cost": 1.1e-07, @@ -66610,7 +66610,7 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { "cache_read_input_token_cost": 2.8e-08, @@ -66620,7 +66620,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4o-2024-05-13": { "input_cost_per_token": 5.5e-06, @@ -66629,7 +66629,7 @@ "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5": { "cache_read_input_token_cost": 1.375e-07, @@ -66642,7 +66642,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { "cache_read_input_token_cost": 1.38e-07, @@ -66650,7 +66650,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-mini": { "cache_read_input_token_cost": 2.75e-08, @@ -66663,7 +66663,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { "cache_read_input_token_cost": 5.5e-09, @@ -66673,7 +66673,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { "input_cost_per_token": 1.65e-05, @@ -66682,7 +66682,7 @@ "mode": "chat", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.375e-07, @@ -66690,7 +66690,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2": { "cache_read_input_token_cost": 1.925e-07, @@ -66703,7 +66703,7 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -66711,7 +66711,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -66719,7 +66719,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-pro": { "input_cost_per_token": 2.31e-05, @@ -66728,7 +66728,7 @@ "mode": "chat", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -66736,7 +66736,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -66747,7 +66747,7 @@ "mode": "chat", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { "cache_read_input_token_cost": 8.25e-08, @@ -66760,7 +66760,7 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { "cache_read_input_token_cost": 2.2e-08, @@ -66770,7 +66770,7 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { "input_cost_per_token": 3.3e-05, @@ -66781,7 +66781,7 @@ "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_batches": 9.9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-6-astra": { "cache_creation_input_token_cost": 1.375e-05, @@ -66794,7 +66794,7 @@ "mode": "chat", "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o1-mini": { "cache_read_input_token_cost": 6.05e-07, @@ -66804,7 +66804,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o1-preview": { "cache_read_input_token_cost": 8.25e-06, @@ -66812,7 +66812,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { "cache_read_input_token_cost": 5.5e-07, @@ -66822,7 +66822,7 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { "cache_read_input_token_cost": 2.75e-06, @@ -66830,7 +66830,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, @@ -66840,25 +66840,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-small": { "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-ada-002": { "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "gemini/gemini-3.8-live": { "input_cost_per_audio_token": 3e-06, @@ -66902,14 +66902,14 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/computer-use-preview": { "input_cost_per_token": 3.3e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.32e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1": { "cache_read_input_token_cost": 5.5e-07, @@ -66922,7 +66922,7 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { "cache_read_input_token_cost": 1.1e-07, @@ -66935,7 +66935,7 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { "cache_read_input_token_cost": 2.8e-08, @@ -66945,7 +66945,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4o-2024-05-13": { "input_cost_per_token": 5.5e-06, @@ -66954,7 +66954,7 @@ "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5": { "cache_read_input_token_cost": 1.375e-07, @@ -66967,7 +66967,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { "cache_read_input_token_cost": 1.38e-07, @@ -66975,7 +66975,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini": { "cache_read_input_token_cost": 2.75e-08, @@ -66988,7 +66988,7 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { "cache_read_input_token_cost": 5.5e-09, @@ -66998,7 +66998,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { "input_cost_per_token": 1.65e-05, @@ -67007,7 +67007,7 @@ "mode": "chat", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.375e-07, @@ -67015,7 +67015,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2": { "cache_read_input_token_cost": 1.925e-07, @@ -67028,7 +67028,7 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -67036,7 +67036,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -67044,7 +67044,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-pro": { "input_cost_per_token": 2.31e-05, @@ -67053,7 +67053,7 @@ "mode": "chat", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, @@ -67061,7 +67061,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { "cache_read_input_token_cost": 1.925e-07, @@ -67072,7 +67072,7 @@ "mode": "chat", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { "cache_read_input_token_cost": 8.25e-08, @@ -67085,7 +67085,7 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { "cache_read_input_token_cost": 2.2e-08, @@ -67095,7 +67095,7 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { "input_cost_per_token": 3.3e-05, @@ -67106,7 +67106,7 @@ "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_batches": 9.9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-mini": { "cache_read_input_token_cost": 6.05e-07, @@ -67116,7 +67116,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-preview": { "cache_read_input_token_cost": 8.25e-06, @@ -67124,7 +67124,7 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o3-deep-research": { "cache_read_input_token_cost": 2.75e-06, @@ -67132,25 +67132,25 @@ "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-large": { "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-small": { "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-ada-002": { "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "aihubmix/agnes-2.5-flash": { "input_cost_per_token": 3e-08, From cab6732928b3a1914a8b91d790b337fa49b7b0c6 Mon Sep 17 00:00:00 2001 From: kerry Date: Wed, 16 Sep 2026 16:32:37 +0000 Subject: [PATCH 17/19] test: drop price-pinning tests that break on catalog updates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../test_azure_ai_fw_models_metadata.py | 31 ------------------- .../proxy/spend_tracking/test_savings.py | 23 -------------- 2 files changed, 54 deletions(-) diff --git a/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py b/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py index 1b2ca298694..c8365e7b7c0 100644 --- a/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py +++ b/tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py @@ -38,37 +38,6 @@ def use_local_model_cost_map(): monkeypatch.undo() -@pytest.mark.parametrize( - "model_name,expected_prompt,expected_completion", - [ - ("FW-Kimi-K2.6", 1.045, 4.4), - ("FW-DeepSeek-V4-Pro", 1.925, 3.828), - ("FW-GLM-5.2", 1.54, 4.84), - ("FW-Kimi-K3", 3.3, 16.5), - ("FW-MiniMax-M2.5", 0.33, 1.32), - ("FW-Inkling", 1.0, 4.05), - ("FW-Nemotron-3-Ultra-NVFP4", 0.6, 2.4), - ("FW-Nemotron-Lightning-3.5-30B-A3B", 0.06, 0.22), - ], -) -def test_azure_ai_fw_cost_per_token( - use_local_model_cost_map, model_name, expected_prompt, expected_completion -): - from litellm.llms.azure_ai.cost_calculator import cost_per_token - from litellm.types.utils import Usage - - usage = Usage( - prompt_tokens=1_000_000, - completion_tokens=1_000_000, - total_tokens=2_000_000, - ) - - prompt_cost, completion_cost = cost_per_token(model=model_name, usage=usage) - - assert prompt_cost == pytest.approx(expected_prompt) - assert completion_cost == pytest.approx(expected_completion) - - def test_azure_ai_fw_nemotron_lightning_supports_tool_choice(use_local_model_cost_map): from litellm.llms.azure_ai.chat.transformation import AzureAIStudioConfig diff --git a/tests/test_litellm/proxy/spend_tracking/test_savings.py b/tests/test_litellm/proxy/spend_tracking/test_savings.py index f90d5daf768..615938f2e33 100644 --- a/tests/test_litellm/proxy/spend_tracking/test_savings.py +++ b/tests/test_litellm/proxy/spend_tracking/test_savings.py @@ -356,29 +356,6 @@ def test_openai_style_cache_write_tokens_are_netted_out(): ) -def test_sub_input_cache_write_price_is_an_extra_saving(): - """A few models price writes below input; there the premium is a real credit. - - Clamping the premium at zero would silently undercount these, so the subtraction - stays signed. ``azure/eu/gpt-4o-2024-11-20`` ships a write price at ~0.5x input. - """ - model = "azure/eu/gpt-4o-2024-11-20" - info = litellm.get_model_info(model=model) - input_cost = info["input_cost_per_token"] - cheap_write = info["cache_creation_input_token_cost"] - assert 0 < cheap_write < input_cost, "fixture drifted: this test needs a model pricing cache writes below input" - - result = compute_savings_spend( - model=model, - custom_llm_provider=None, - compression_saved_tokens=0, - gateway_injected_cache=True, - usage_object=_caching_usage(read=1000, written=4000), - ) - assert result.prompt_caching == pytest.approx(4000 * (input_cost - cheap_write)) - assert result.prompt_caching > 0 - - def test_negative_cache_write_count_clamps_to_zero(): """A malformed negative write count must not be read as a saving.""" input_cost, cache_read_cost = _anthropic_costs("claude-sonnet-5") From eed760a37d91d462bfaa5e8c068ceadf51d21bae Mon Sep 17 00:00:00 2001 From: kerry Date: Wed, 16 Sep 2026 16:49:15 +0000 Subject: [PATCH 18/19] test: drop azure gpt-5.6 rate tests pinned to a dated price page Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- tests/test_litellm/test_cost_calculator.py | 67 ---------------------- 1 file changed, 67 deletions(-) diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index 7b53d3a58df..a5ed7175649 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -1616,73 +1616,6 @@ def test_azure_ai_cache_cost_calculation(_local_model_cost_map): ) -AZURE_GPT_5_6_MAP_KEYS = ( - "azure/gpt-5.6", - "azure/gpt-5.6-sol", - "azure/gpt-5.6-terra", - "azure/gpt-5.6-luna", - "azure/us/gpt-5.6", - "azure/us/gpt-5.6-sol", - "azure/us/gpt-5.6-terra", - "azure/us/gpt-5.6-luna", - "azure/eu/gpt-5.6", - "azure/eu/gpt-5.6-sol", - "azure/eu/gpt-5.6-terra", - "azure/eu/gpt-5.6-luna", -) - - -def test_azure_gpt_5_6_cache_write_tokens_are_billed(_local_model_cost_map): - """ - Azure bills gpt-5.6 prompt cache writes at 1.25x the input rate on every - tier, but the azure entries carried no ``cache_creation_input_token_cost``, - so cache-write tokens were billed at the plain input rate instead. - """ - from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token - from litellm.types.utils import PromptTokensDetailsWrapper, Usage - - usage = Usage( - completion_tokens=100, - prompt_tokens=2000, - total_tokens=2100, - prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=0, text_tokens=687), - cache_creation_input_tokens=1313, - ) - - input_cost, output_cost = generic_cost_per_token( - model="azure/gpt-5.6-luna", usage=usage, custom_llm_provider="azure" - ) - - assert input_cost == pytest.approx(687 * 2e-07 + 1313 * 2.5e-07) - assert output_cost == pytest.approx(100 * 1.2e-06) - - -@pytest.mark.parametrize("model", AZURE_GPT_5_6_MAP_KEYS) -def test_azure_gpt_5_6_rates_match_azure_price_page(_local_model_cost_map, model): - """ - Per the Azure OpenAI price page (rendered 2026-08-26): cache writes cost - 1.25x input on every gpt-5.6 tier, and Data Zone costs 1.1x Global for - standard and priority alike (us/eu priority rates previously sat at 1.25x). - """ - entry = litellm.model_cost[model] - input_keys = [key for key in entry if key.startswith("input_cost_per_token")] - assert input_keys - for key in input_keys: - suffix = key[len("input_cost_per_token") :] - assert entry["cache_creation_input_token_cost" + suffix] == pytest.approx(entry[key] * 1.25) - - zone = model.split("/")[1] - if zone in ("us", "eu"): - global_entry = litellm.model_cost["azure/" + model.split("/", 2)[2]] - prefixes = ("input_cost_per_token", "output_cost_per_token", "cache_read", "cache_creation") - token_cost_keys = [key for key in entry if key.startswith(prefixes)] - global_token_cost_keys = [key for key in global_entry if key.startswith(prefixes)] - assert len(token_cost_keys) >= 9 - assert sorted(token_cost_keys) == sorted(global_token_cost_keys) - for key in token_cost_keys: - assert entry[key] == pytest.approx(global_entry[key] * 1.1), key - - def test_vertex_regional_deployment_costs_uplift_over_global(monkeypatch): """ Regression for https://github.com/BerriAI/litellm/issues/34393: two Vertex From b9ab36279b05d0a96e528385e30b71a9e32f8cc0 Mon Sep 17 00:00:00 2001 From: kerry Date: Wed, 16 Sep 2026 16:49:17 +0000 Subject: [PATCH 19/19] fix(prices): add tpm and rpm to gemini 3.8 live rows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 4 ++++ model_prices_and_context_window.json | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 27344af1991..cd458666539 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -66873,6 +66873,8 @@ "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, @@ -66891,6 +66893,8 @@ "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 27344af1991..cd458666539 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -66873,6 +66873,8 @@ "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, @@ -66891,6 +66893,8 @@ "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true,