From e7460f1cff7fc1b6e323c9e4a969fe6b4609d164 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, 29 Sep 2026 16:07:08 -0700 Subject: [PATCH] chore(cost-map): take azure context limits from models-sold-directly (#43759) Price-Sync: litellm-providers Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 92 ++++++++++++------- model_prices_and_context_window.json | 92 ++++++++++++------- 2 files changed, 114 insertions(+), 70 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 99471d48f56..9989846b7e0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3977,7 +3977,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4112,7 +4112,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4159,7 +4159,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4206,7 +4206,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4254,7 +4254,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4302,7 +4302,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4348,7 +4348,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4678,12 +4678,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 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", "supported_modalities": [ "text", "audio" @@ -6319,12 +6320,13 @@ "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -6370,6 +6372,9 @@ "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "audio_transcription", "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ @@ -7424,7 +7429,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7480,7 +7485,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7530,7 +7535,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7580,7 +7585,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7636,7 +7641,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7686,7 +7691,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7737,7 +7742,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -7786,7 +7791,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -9374,7 +9379,7 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9433,7 +9438,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9488,7 +9493,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9540,7 +9545,7 @@ "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, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9600,7 +9605,7 @@ "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9659,7 +9664,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9712,7 +9717,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9766,7 +9771,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9819,7 +9824,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -11100,12 +11105,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 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", "supported_modalities": [ "text", "audio" @@ -11504,6 +11510,8 @@ }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -11513,6 +11521,8 @@ }, "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", @@ -11922,8 +11932,8 @@ "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12462,9 +12472,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -12476,9 +12486,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "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, @@ -70560,6 +70570,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -70850,6 +70863,9 @@ "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, @@ -70870,6 +70886,9 @@ "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, @@ -70998,6 +71017,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 99471d48f56..9989846b7e0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3977,7 +3977,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4112,7 +4112,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4159,7 +4159,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4206,7 +4206,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4254,7 +4254,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4302,7 +4302,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4348,7 +4348,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4678,12 +4678,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 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", "supported_modalities": [ "text", "audio" @@ -6319,12 +6320,13 @@ "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -6370,6 +6372,9 @@ "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "audio_transcription", "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ @@ -7424,7 +7429,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7480,7 +7485,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7530,7 +7535,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7580,7 +7585,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7636,7 +7641,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7686,7 +7691,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7737,7 +7742,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -7786,7 +7791,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -9374,7 +9379,7 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9433,7 +9438,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9488,7 +9493,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9540,7 +9545,7 @@ "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, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9600,7 +9605,7 @@ "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9659,7 +9664,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9712,7 +9717,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9766,7 +9771,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9819,7 +9824,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -11100,12 +11105,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 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", "supported_modalities": [ "text", "audio" @@ -11504,6 +11510,8 @@ }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -11513,6 +11521,8 @@ }, "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", @@ -11922,8 +11932,8 @@ "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "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'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12462,9 +12472,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -12476,9 +12486,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -70560,6 +70570,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -70850,6 +70863,9 @@ "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, @@ -70870,6 +70886,9 @@ "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, @@ -70998,6 +71017,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06,