diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f53b2e5dbd7..47dd58c5037 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4691,9 +4691,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" @@ -5752,14 +5752,14 @@ }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" @@ -5781,19 +5781,20 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5948,15 +5949,16 @@ "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -6355,27 +6357,28 @@ }, "azure/gpt-4o-transcribe": { "deprecation_date": "2026-10-15", - "input_cost_per_audio_token": 2.5e-06, + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", - "input_cost_per_audio_token": 2.5e-06, + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] @@ -10325,6 +10328,7 @@ "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { + "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, @@ -10332,28 +10336,32 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 4e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, + "input_cost_per_pixel": 8.39233e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", @@ -10446,6 +10454,7 @@ ] }, "azure/gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", "input_cost_per_image_token": 2.5e-06, @@ -10453,12 +10462,14 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10466,12 +10477,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, @@ -10479,12 +10493,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10492,6 +10509,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10500,6 +10518,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-flare": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10507,6 +10526,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10515,6 +10535,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-sunburst": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10522,6 +10543,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10530,6 +10552,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2-2026-04-21": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", "input_cost_per_token": 5e-06, @@ -10537,6 +10560,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10983,22 +11007,25 @@ "output_cost_per_token": 0.0 }, "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, + "input_cost_per_pixel": 4.19617e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", @@ -11284,9 +11311,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f53b2e5dbd7..47dd58c5037 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4691,9 +4691,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" @@ -5752,14 +5752,14 @@ }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" @@ -5781,19 +5781,20 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5948,15 +5949,16 @@ "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -6355,27 +6357,28 @@ }, "azure/gpt-4o-transcribe": { "deprecation_date": "2026-10-15", - "input_cost_per_audio_token": 2.5e-06, + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", - "input_cost_per_audio_token": 2.5e-06, + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] @@ -10325,6 +10328,7 @@ "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { + "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, @@ -10332,28 +10336,32 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 4e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, + "input_cost_per_pixel": 8.39233e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", @@ -10446,6 +10454,7 @@ ] }, "azure/gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", "input_cost_per_image_token": 2.5e-06, @@ -10453,12 +10462,14 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10466,12 +10477,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, @@ -10479,12 +10493,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10492,6 +10509,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10500,6 +10518,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-flare": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10507,6 +10526,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10515,6 +10535,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-sunburst": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10522,6 +10543,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10530,6 +10552,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2-2026-04-21": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", "input_cost_per_token": 5e-06, @@ -10537,6 +10560,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10983,22 +11007,25 @@ "output_cost_per_token": 0.0 }, "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, + "input_cost_per_pixel": 4.19617e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", @@ -11284,9 +11311,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio"