scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

fix: update stale source URLs in model cost map

Browse source 
119 entries pointed at 404ing or permanently-moved pages (Pylon #7777).
Replaced with verified working equivalents (200-checked or permanent
redirect targets).

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-29 20:56:21 +00:00
parent 645792955d
commit 5024c4d520
2 changed files with 238 additions and 238 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

238
litellm/model_prices_and_context_window_backup.json
View file

@ -3726,7 +3726,7 @@
"output_cost_per_token": 0,
"litellm_provider": "azure_ai",
"mode": "chat",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/",
"comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/<deployment-name> where deployment-name is your Azure deployment (e.g., azure-model-router)"
},
"azure/eu/gpt-4o-2024-08-06": {
@ -5328,7 +5328,7 @@
"input_cost_per_second": 0.0002833333333333333,
"litellm_provider": "azure",
"mode": "audio_transcription",
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper",
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper",
"supported_endpoints": [
"/v1/realtime",
"/v1/realtime/transcription_sessions"
@ -9107,7 +9107,7 @@
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"supports_embedding_image_input": true
},
"azure_ai/Cohere-embed-v3-multilingual": {
@ -9118,7 +9118,7 @@
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"supports_embedding_image_input": true
},
"azure_ai/FLUX-1.1-pro": {
@ -9134,7 +9134,7 @@
"litellm_provider": "azure_ai",
"mode": "image_generation",
"output_cost_per_image": 0.04,
"source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"supported_endpoints": [
"/v1/images/generations"
]
@ -9467,7 +9467,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.7e-07,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
@ -9481,7 +9481,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 2.04e-06,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
@ -9494,7 +9494,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 7.1e-07,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -9543,7 +9543,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 1.6e-05,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-70B-Instruct": {
@ -9554,7 +9554,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.54e-06,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-8B-Instruct": {
@ -9566,7 +9566,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 6.1e-07,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice",
"supports_tool_choice": true
},
"azure_ai/Phi-3-medium-128k-instruct": {
@ -9756,7 +9756,7 @@
"supported_endpoints": [
"/v1/ocr"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/"
"source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512"
},
"azure_ai/doc-intelligence/prebuilt-read": {
"litellm_provider": "azure_ai",
@ -9967,7 +9967,7 @@
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 3072,
"source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"supported_endpoints": [
"/v1/embeddings"
],
@ -10151,7 +10151,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.00971,
"source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat"
"source": "https://ai.azure.com/catalog/models/jais-30b-chat"
},
"azure_ai/jamba-instruct": {
"input_cost_per_token": 5e-07,
@ -10208,7 +10208,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-08,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -10231,7 +10231,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -10243,7 +10243,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -10280,7 +10280,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.5e-07,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
"supports_function_calling": true
},
"azure_ai/mistral-small": {
@ -22796,7 +22796,7 @@
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -22850,7 +22850,7 @@
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -22915,7 +22915,7 @@
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -22974,7 +22974,7 @@
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23178,7 +23178,7 @@
"mode": "chat",
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23262,7 +23262,7 @@
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23325,7 +23325,7 @@
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23382,7 +23382,7 @@
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -26982,7 +26982,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://platform.openai.com/docs/models/gpt-5.6-cyber",
"source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber",
"supports_computer_use": true,
"supports_parallel_function_calling": true
},
@ -27021,7 +27021,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://platform.openai.com/docs/models/daybreak-red-latest",
"source": "https://developers.openai.com/api/docs/models/daybreak-red-latest",
"supports_computer_use": true,
"supports_parallel_function_calling": true
},
@ -27061,7 +27061,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://platform.openai.com/docs/models/daybreak-blue-latest",
"source": "https://developers.openai.com/api/docs/models/daybreak-blue-latest",
"supports_parallel_function_calling": true
},
"chat-latest": {
@ -27073,7 +27073,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"source": "https://platform.openai.com/docs/models/chat-latest",
"source": "https://developers.openai.com/api/docs/models/chat-latest",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
@ -30368,7 +30368,7 @@
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
@ -30409,7 +30409,7 @@
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
@ -30450,7 +30450,7 @@
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
@ -30483,7 +30483,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text"
],
@ -30499,7 +30499,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text"
],
@ -30515,7 +30515,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text",
"image"
@ -30532,7 +30532,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text",
"image"
@ -32477,7 +32477,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-R1-0528": {
"max_tokens": 164000,
@ -32489,7 +32489,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
"max_tokens": 128000,
@ -32500,7 +32500,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-V3": {
"max_tokens": 128000,
@ -32511,7 +32511,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-V3-0324": {
"max_tokens": 128000,
@ -32522,7 +32522,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/google/gemma-3-27b-it": {
"max_tokens": 128000,
@ -32534,7 +32534,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Llama-3.3-70B-Instruct": {
"max_tokens": 128000,
@ -32545,7 +32545,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Llama-Guard-3-8B": {
"max_tokens": 128000,
@ -32555,7 +32555,7 @@
"output_cost_per_token": 6e-08,
"litellm_provider": "nebius",
"mode": "chat",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": {
"max_tokens": 128000,
@ -32566,7 +32566,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": {
"max_tokens": 128000,
@ -32577,7 +32577,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": {
"max_tokens": 128000,
@ -32588,7 +32588,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/mistralai/Mistral-Nemo-Instruct-2407": {
"max_tokens": 128000,
@ -32599,7 +32599,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/NousResearch/Hermes-3-Llama-3.1-405B": {
"max_tokens": 128000,
@ -32610,7 +32610,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": {
"max_tokens": 128000,
@ -32621,7 +32621,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": {
"max_tokens": 131072,
@ -32632,7 +32632,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-235B-A22B": {
"max_tokens": 262144,
@ -32643,7 +32643,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-32B": {
"max_tokens": 32768,
@ -32654,7 +32654,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-30B-A3B": {
"max_tokens": 32768,
@ -32665,7 +32665,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-14B": {
"max_tokens": 32768,
@ -32676,7 +32676,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-4B": {
"max_tokens": 32768,
@ -32687,7 +32687,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/QwQ-32B": {
"max_tokens": 32768,
@ -32699,7 +32699,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-72B-Instruct": {
"max_tokens": 128000,
@ -32710,7 +32710,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-32B-Instruct": {
"max_tokens": 128000,
@ -32721,7 +32721,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-Coder-7B": {
"max_tokens": 32768,
@ -32732,7 +32732,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-VL-72B-Instruct": {
"max_tokens": 131072,
@ -32744,7 +32744,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2-VL-72B-Instruct": {
"max_tokens": 131072,
@ -32756,7 +32756,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2-VL-7B-Instruct": {
"max_tokens": 131072,
@ -32767,7 +32767,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/BAAI/bge-en-icl": {
"max_tokens": 32768,
@ -32776,7 +32776,7 @@
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/BAAI/bge-multilingual-gemma2": {
"max_tokens": 8192,
@ -32785,7 +32785,7 @@
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/intfloat/e5-mistral-7b-instruct": {
"max_tokens": 32768,
@ -32794,7 +32794,7 @@
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nvidia.nemotron-nano-12b-v2": {
"input_cost_per_token": 2e-07,
@ -33535,7 +33535,7 @@
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33548,7 +33548,7 @@
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33561,7 +33561,7 @@
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33618,7 +33618,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true,
@ -33632,7 +33632,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": false,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33643,7 +33643,7 @@
"max_input_tokens": 512,
"mode": "embedding",
"output_vector_size": 1024,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_vision": true
},
"oci/cohere.command-a-reasoning-08-2025": {
@ -34540,7 +34540,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b",
"source": "https://openrouter.ai/bytedance/ui-tars-1.5-7b",
"supports_tool_choice": true
},
"openrouter/deepseek/deepseek-chat": {
@ -34775,7 +34775,7 @@
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -34816,7 +34816,7 @@
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -35901,7 +35901,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 6.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -35915,7 +35915,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35928,7 +35928,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 6.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": false,
"supports_tool_choice": false
@ -35941,7 +35941,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 6.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35954,7 +35954,7 @@
"max_tokens": 127000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35967,7 +35967,7 @@
"max_tokens": 118000,
"mode": "chat",
"output_cost_per_token": 1.3e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35980,7 +35980,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -35994,7 +35994,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 6.3e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false
@ -36007,7 +36007,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 8.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false
@ -36020,7 +36020,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 9.1e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false,
@ -36034,7 +36034,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.3e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -36048,7 +36048,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 4e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_reasoning": true,
"supports_response_schema": true,
@ -36062,7 +36062,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.5e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_reasoning": true,
"supports_response_schema": true,
@ -36076,7 +36076,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.9e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false,
@ -36090,7 +36090,7 @@
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 1.9e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false
@ -38856,7 +38856,7 @@
"max_input_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B",
"source": "https://www.together.ai/models/qwen3-5-397b-a17b",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
@ -43097,7 +43097,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -43113,7 +43113,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -43130,7 +43130,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -43146,7 +43146,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -43266,7 +43266,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -43280,7 +43280,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -43295,7 +43295,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -43310,7 +43310,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -44946,7 +44946,7 @@
"litellm_provider": "azure",
"mode": "video_generation",
"output_cost_per_video_per_second": 0.1,
"source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
"source": "https://ai.azure.com/catalog/models/sora-2",
"supported_modalities": [
"text"
],
@ -44958,7 +44958,7 @@
"litellm_provider": "azure",
"mode": "video_generation",
"output_cost_per_video_per_second": 0.3,
"source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
"source": "https://ai.azure.com/catalog/models/sora-2-pro",
"supported_modalities": [
"text"
],
@ -44970,7 +44970,7 @@
"litellm_provider": "azure",
"mode": "video_generation",
"output_cost_per_video_per_second": 0.5,
"source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
"source": "https://ai.azure.com/catalog/models/sora-2-pro",
"supported_modalities": [
"text"
],
@ -49180,7 +49180,7 @@
"input_cost_per_second": 0.0002833333333333333,
"litellm_provider": "openai",
"mode": "audio_transcription",
"source": "https://platform.openai.com/docs/models/gpt-realtime-whisper",
"source": "https://developers.openai.com/api/docs/models/gpt-realtime-whisper",
"supported_endpoints": [
"/v1/realtime",
"/v1/realtime/transcription_sessions"
@ -50432,7 +50432,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -50470,7 +50470,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -50508,7 +50508,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -50546,7 +50546,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -51295,7 +51295,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/qwen3.6-35b-a3b": {
"max_tokens": 131072,
@ -51308,7 +51308,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/qwen3-30b-a3b": {
"max_tokens": 131072,
@ -51321,7 +51321,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/qwen3-coder-30b-a3b": {
"max_tokens": 131072,
@ -51334,7 +51334,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": false,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/deepseek-v4-flash": {
"max_tokens": 163840,
@ -51347,7 +51347,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/minimax-m2.7": {
"max_tokens": 1000192,
@ -51360,7 +51360,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": false,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
@ -51464,7 +51464,7 @@
"input_cost_per_second": 7.5e-05,
"litellm_provider": "openai",
"mode": "audio_transcription",
"source": "https://platform.openai.com/docs/models/gpt-transcribe",
"source": "https://developers.openai.com/api/docs/models/gpt-transcribe",
"supported_endpoints": [
"/v1/audio/transcriptions",
"/v1/realtime/transcription_sessions"
@ -51482,7 +51482,7 @@
"input_cost_per_second": 0.0002833333333333333,
"litellm_provider": "openai",
"mode": "audio_transcription",
"source": "https://platform.openai.com/docs/models/gpt-live-transcribe",
"source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe",
"supported_endpoints": [
"/v1/realtime",
"/v1/realtime/transcription_sessions"
@ -51503,7 +51503,7 @@
"max_output_tokens": 2000,
"max_tokens": 2000,
"mode": "realtime",
"source": "https://platform.openai.com/docs/models/gpt-realtime-translate",
"source": "https://developers.openai.com/api/docs/models/gpt-realtime-translate",
"supported_modalities": [
"audio"
],
@ -51531,7 +51531,7 @@
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://docs.claude.com/en/docs/about-claude/models/overview",
"source": "https://platform.claude.com/docs/en/about-claude/models/overview",
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_mid_conversation_system": true,
@ -51570,7 +51570,7 @@
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://docs.claude.com/en/docs/about-claude/models/overview",
"source": "https://platform.claude.com/docs/en/about-claude/models/overview",
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,

238
model_prices_and_context_window.json
View file

@ -3726,7 +3726,7 @@
"output_cost_per_token": 0,
"litellm_provider": "azure_ai",
"mode": "chat",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/",
"comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/<deployment-name> where deployment-name is your Azure deployment (e.g., azure-model-router)"
},
"azure/eu/gpt-4o-2024-08-06": {
@ -5328,7 +5328,7 @@
"input_cost_per_second": 0.0002833333333333333,
"litellm_provider": "azure",
"mode": "audio_transcription",
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper",
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper",
"supported_endpoints": [
"/v1/realtime",
"/v1/realtime/transcription_sessions"
@ -9107,7 +9107,7 @@
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"supports_embedding_image_input": true
},
"azure_ai/Cohere-embed-v3-multilingual": {
@ -9118,7 +9118,7 @@
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
"supports_embedding_image_input": true
},
"azure_ai/FLUX-1.1-pro": {
@ -9134,7 +9134,7 @@
"litellm_provider": "azure_ai",
"mode": "image_generation",
"output_cost_per_image": 0.04,
"source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"supported_endpoints": [
"/v1/images/generations"
]
@ -9467,7 +9467,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.7e-07,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
@ -9481,7 +9481,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 2.04e-06,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
@ -9494,7 +9494,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 7.1e-07,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -9543,7 +9543,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 1.6e-05,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-70B-Instruct": {
@ -9554,7 +9554,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.54e-06,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-8B-Instruct": {
@ -9566,7 +9566,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 6.1e-07,
"source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice",
"supports_tool_choice": true
},
"azure_ai/Phi-3-medium-128k-instruct": {
@ -9756,7 +9756,7 @@
"supported_endpoints": [
"/v1/ocr"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/"
"source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512"
},
"azure_ai/doc-intelligence/prebuilt-read": {
"litellm_provider": "azure_ai",
@ -9967,7 +9967,7 @@
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 3072,
"source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
"supported_endpoints": [
"/v1/embeddings"
],
@ -10151,7 +10151,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.00971,
"source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat"
"source": "https://ai.azure.com/catalog/models/jais-30b-chat"
},
"azure_ai/jamba-instruct": {
"input_cost_per_token": 5e-07,
@ -10208,7 +10208,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-08,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -10231,7 +10231,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -10243,7 +10243,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -10280,7 +10280,7 @@
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.5e-07,
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
"source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
"supports_function_calling": true
},
"azure_ai/mistral-small": {
@ -22796,7 +22796,7 @@
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -22850,7 +22850,7 @@
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -22915,7 +22915,7 @@
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -22974,7 +22974,7 @@
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23178,7 +23178,7 @@
"mode": "chat",
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23262,7 +23262,7 @@
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23325,7 +23325,7 @@
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -23382,7 +23382,7 @@
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -26982,7 +26982,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://platform.openai.com/docs/models/gpt-5.6-cyber",
"source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber",
"supports_computer_use": true,
"supports_parallel_function_calling": true
},
@ -27021,7 +27021,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://platform.openai.com/docs/models/daybreak-red-latest",
"source": "https://developers.openai.com/api/docs/models/daybreak-red-latest",
"supports_computer_use": true,
"supports_parallel_function_calling": true
},
@ -27061,7 +27061,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://platform.openai.com/docs/models/daybreak-blue-latest",
"source": "https://developers.openai.com/api/docs/models/daybreak-blue-latest",
"supports_parallel_function_calling": true
},
"chat-latest": {
@ -27073,7 +27073,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"source": "https://platform.openai.com/docs/models/chat-latest",
"source": "https://developers.openai.com/api/docs/models/chat-latest",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
@ -30368,7 +30368,7 @@
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
@ -30409,7 +30409,7 @@
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
@ -30450,7 +30450,7 @@
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
@ -30483,7 +30483,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text"
],
@ -30499,7 +30499,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text"
],
@ -30515,7 +30515,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text",
"image"
@ -30532,7 +30532,7 @@
"max_output_tokens": 4028,
"max_tokens": 4028,
"mode": "chat",
"source": "https://llama.developer.meta.com/docs/models",
"source": "https://ai.developer.meta.com/docs/models",
"supported_modalities": [
"text",
"image"
@ -32477,7 +32477,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-R1-0528": {
"max_tokens": 164000,
@ -32489,7 +32489,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
"max_tokens": 128000,
@ -32500,7 +32500,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-V3": {
"max_tokens": 128000,
@ -32511,7 +32511,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/deepseek-ai/DeepSeek-V3-0324": {
"max_tokens": 128000,
@ -32522,7 +32522,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/google/gemma-3-27b-it": {
"max_tokens": 128000,
@ -32534,7 +32534,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Llama-3.3-70B-Instruct": {
"max_tokens": 128000,
@ -32545,7 +32545,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Llama-Guard-3-8B": {
"max_tokens": 128000,
@ -32555,7 +32555,7 @@
"output_cost_per_token": 6e-08,
"litellm_provider": "nebius",
"mode": "chat",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": {
"max_tokens": 128000,
@ -32566,7 +32566,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": {
"max_tokens": 128000,
@ -32577,7 +32577,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": {
"max_tokens": 128000,
@ -32588,7 +32588,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/mistralai/Mistral-Nemo-Instruct-2407": {
"max_tokens": 128000,
@ -32599,7 +32599,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/NousResearch/Hermes-3-Llama-3.1-405B": {
"max_tokens": 128000,
@ -32610,7 +32610,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": {
"max_tokens": 128000,
@ -32621,7 +32621,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": {
"max_tokens": 131072,
@ -32632,7 +32632,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-235B-A22B": {
"max_tokens": 262144,
@ -32643,7 +32643,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-32B": {
"max_tokens": 32768,
@ -32654,7 +32654,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-30B-A3B": {
"max_tokens": 32768,
@ -32665,7 +32665,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-14B": {
"max_tokens": 32768,
@ -32676,7 +32676,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen3-4B": {
"max_tokens": 32768,
@ -32687,7 +32687,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/QwQ-32B": {
"max_tokens": 32768,
@ -32699,7 +32699,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-72B-Instruct": {
"max_tokens": 128000,
@ -32710,7 +32710,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-32B-Instruct": {
"max_tokens": 128000,
@ -32721,7 +32721,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-Coder-7B": {
"max_tokens": 32768,
@ -32732,7 +32732,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2.5-VL-72B-Instruct": {
"max_tokens": 131072,
@ -32744,7 +32744,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2-VL-72B-Instruct": {
"max_tokens": 131072,
@ -32756,7 +32756,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/Qwen/Qwen2-VL-7B-Instruct": {
"max_tokens": 131072,
@ -32767,7 +32767,7 @@
"litellm_provider": "nebius",
"mode": "chat",
"supports_vision": true,
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/BAAI/bge-en-icl": {
"max_tokens": 32768,
@ -32776,7 +32776,7 @@
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/BAAI/bge-multilingual-gemma2": {
"max_tokens": 8192,
@ -32785,7 +32785,7 @@
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nebius/intfloat/e5-mistral-7b-instruct": {
"max_tokens": 32768,
@ -32794,7 +32794,7 @@
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding",
"source": "https://nebius.com/prices-ai-studio"
"source": "https://nebius.com/prices"
},
"nvidia.nemotron-nano-12b-v2": {
"input_cost_per_token": 2e-07,
@ -33535,7 +33535,7 @@
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33548,7 +33548,7 @@
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33561,7 +33561,7 @@
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33618,7 +33618,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true,
@ -33632,7 +33632,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.56e-06,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_function_calling": false,
"supports_response_schema": false,
"supports_native_streaming": true
@ -33643,7 +33643,7 @@
"max_input_tokens": 512,
"mode": "embedding",
"output_vector_size": 1024,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/",
"supports_vision": true
},
"oci/cohere.command-a-reasoning-08-2025": {
@ -34540,7 +34540,7 @@
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b",
"source": "https://openrouter.ai/bytedance/ui-tars-1.5-7b",
"supports_tool_choice": true
},
"openrouter/deepseek/deepseek-chat": {
@ -34775,7 +34775,7 @@
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -34816,7 +34816,7 @@
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"rpm": 2000,
"source": "https://ai.google.dev/pricing/gemini-3",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -35901,7 +35901,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 6.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -35915,7 +35915,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35928,7 +35928,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 6.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": false,
"supports_tool_choice": false
@ -35941,7 +35941,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 6.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35954,7 +35954,7 @@
"max_tokens": 127000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35967,7 +35967,7 @@
"max_tokens": 118000,
"mode": "chat",
"output_cost_per_token": 1.3e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -35980,7 +35980,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -35994,7 +35994,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 6.3e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false
@ -36007,7 +36007,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 8.7e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false
@ -36020,7 +36020,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 9.1e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false,
@ -36034,7 +36034,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.3e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -36048,7 +36048,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 4e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_reasoning": true,
"supports_response_schema": true,
@ -36062,7 +36062,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.5e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_reasoning": true,
"supports_response_schema": true,
@ -36076,7 +36076,7 @@
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.9e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false,
@ -36090,7 +36090,7 @@
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 1.9e-07,
"source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1",
"source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": false
@ -38856,7 +38856,7 @@
"max_input_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B",
"source": "https://www.together.ai/models/qwen3-5-397b-a17b",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
@ -43097,7 +43097,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -43113,7 +43113,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -43130,7 +43130,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -43146,7 +43146,7 @@
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"source": "https://docs.x.ai/developers/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -43266,7 +43266,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -43280,7 +43280,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -43295,7 +43295,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -43310,7 +43310,7 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"supported_modalities": [
"text"
],
@ -44946,7 +44946,7 @@
"litellm_provider": "azure",
"mode": "video_generation",
"output_cost_per_video_per_second": 0.1,
"source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
"source": "https://ai.azure.com/catalog/models/sora-2",
"supported_modalities": [
"text"
],
@ -44958,7 +44958,7 @@
"litellm_provider": "azure",
"mode": "video_generation",
"output_cost_per_video_per_second": 0.3,
"source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
"source": "https://ai.azure.com/catalog/models/sora-2-pro",
"supported_modalities": [
"text"
],
@ -44970,7 +44970,7 @@
"litellm_provider": "azure",
"mode": "video_generation",
"output_cost_per_video_per_second": 0.5,
"source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
"source": "https://ai.azure.com/catalog/models/sora-2-pro",
"supported_modalities": [
"text"
],
@ -49180,7 +49180,7 @@
"input_cost_per_second": 0.0002833333333333333,
"litellm_provider": "openai",
"mode": "audio_transcription",
"source": "https://platform.openai.com/docs/models/gpt-realtime-whisper",
"source": "https://developers.openai.com/api/docs/models/gpt-realtime-whisper",
"supported_endpoints": [
"/v1/realtime",
"/v1/realtime/transcription_sessions"
@ -50432,7 +50432,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -50470,7 +50470,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -50508,7 +50508,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -50546,7 +50546,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://www.volcengine.com/docs/82379/1330310",
"source": "https://docs.volcengine.com/docs/82379/1330310",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": false,
@ -51295,7 +51295,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/qwen3.6-35b-a3b": {
"max_tokens": 131072,
@ -51308,7 +51308,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/qwen3-30b-a3b": {
"max_tokens": 131072,
@ -51321,7 +51321,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/qwen3-coder-30b-a3b": {
"max_tokens": 131072,
@ -51334,7 +51334,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": false,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/deepseek-v4-flash": {
"max_tokens": 163840,
@ -51347,7 +51347,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"pinstripes/ps/minimax-m2.7": {
"max_tokens": 1000192,
@ -51360,7 +51360,7 @@
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": false,
"source": "https://pinstripes.io/pricing"
"source": "https://pinstripes.io/"
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
@ -51464,7 +51464,7 @@
"input_cost_per_second": 7.5e-05,
"litellm_provider": "openai",
"mode": "audio_transcription",
"source": "https://platform.openai.com/docs/models/gpt-transcribe",
"source": "https://developers.openai.com/api/docs/models/gpt-transcribe",
"supported_endpoints": [
"/v1/audio/transcriptions",
"/v1/realtime/transcription_sessions"
@ -51482,7 +51482,7 @@
"input_cost_per_second": 0.0002833333333333333,
"litellm_provider": "openai",
"mode": "audio_transcription",
"source": "https://platform.openai.com/docs/models/gpt-live-transcribe",
"source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe",
"supported_endpoints": [
"/v1/realtime",
"/v1/realtime/transcription_sessions"
@ -51503,7 +51503,7 @@
"max_output_tokens": 2000,
"max_tokens": 2000,
"mode": "realtime",
"source": "https://platform.openai.com/docs/models/gpt-realtime-translate",
"source": "https://developers.openai.com/api/docs/models/gpt-realtime-translate",
"supported_modalities": [
"audio"
],
@ -51531,7 +51531,7 @@
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://docs.claude.com/en/docs/about-claude/models/overview",
"source": "https://platform.claude.com/docs/en/about-claude/models/overview",
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_mid_conversation_system": true,
@ -51570,7 +51570,7 @@
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://docs.claude.com/en/docs/about-claude/models/overview",
"source": "https://platform.claude.com/docs/en/about-claude/models/overview",
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,