scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 84

fix(registry): add gemini 3.8 live, azure gpt-5.5/luna snapshots, doubao seed 2.1, fix together v4.1 flash context

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-15 19:15:46 +00:00
parent 7566164e46
commit 93f27d6082
2 changed files with 844 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

425
litellm/model_prices_and_context_window_backup.json
View file

@ -3781,6 +3781,53 @@
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure_ai/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure_ai/gpt-5.4": {
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.5e-07,
@ -7380,6 +7427,62 @@
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna-2026-07-09": {
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_priority": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_priority": 4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_priority": 2.4e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/gpt-6-astra": {
"cache_creation_input_token_cost": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
@ -8218,6 +8321,58 @@
"supports_web_search": true,
"deprecation_date": "2027-10-26"
},
"azure/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/us/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
@ -8263,6 +8418,55 @@
"supports_web_search": true,
"deprecation_date": "2027-10-26"
},
"azure/us/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.38e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
"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_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/eu/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
@ -8308,6 +8512,55 @@
"supports_web_search": true,
"deprecation_date": "2027-10-26"
},
"azure/eu/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.38e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
"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_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/gpt-5.5-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
@ -44436,11 +44689,11 @@
"cache_read_input_token_cost": 6e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1000000,
"max_tokens": 1000000,
"max_input_tokens": 1048576,
"max_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://docs.together.ai/docs/serverless-models",
"source": "https://api.together.xyz/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
@ -55573,6 +55826,73 @@
"supports_web_search": true,
"gemini_audio_only_live": true
},
"gemini-3.8-live": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true
},
"gemini-3.8-live-extended-thinking": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true,
"supports_reasoning": true
},
"gemini/gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
@ -55692,6 +56012,73 @@
"rpm": 10,
"gemini_audio_only_live": true
},
"gemini/gemini-3.8-live": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true
},
"gemini/gemini-3.8-live-extended-thinking": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true,
"supports_reasoning": true
},
"gemini/gemini-3.1-flash-tts-preview": {
"input_cost_per_token": 1e-06,
"litellm_provider": "gemini",
@ -56850,6 +57237,38 @@
}
]
},
"volcengine/doubao-seed-2-1-pro-260628": {
"cache_read_input_token_cost": 1.725e-07,
"input_cost_per_token": 8.625e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 4.3125e-06,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-turbo-260628": {
"cache_read_input_token_cost": 8.625e-08,
"input_cost_per_token": 4.3125e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 2.15625e-06,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-0-lite-260215": {
"litellm_provider": "volcengine",
"max_input_tokens": 256000,

425
model_prices_and_context_window.json
View file

@ -3781,6 +3781,53 @@
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure_ai/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure_ai/gpt-5.4": {
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.5e-07,
@ -7380,6 +7427,62 @@
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna-2026-07-09": {
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_priority": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_priority": 4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_priority": 2.4e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/gpt-6-astra": {
"cache_creation_input_token_cost": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
@ -8218,6 +8321,58 @@
"supports_web_search": true,
"deprecation_date": "2027-10-26"
},
"azure/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_priority": 6e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/us/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
@ -8263,6 +8418,55 @@
"supports_web_search": true,
"deprecation_date": "2027-10-26"
},
"azure/us/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.38e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
"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_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/eu/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
@ -8308,6 +8512,55 @@
"supports_web_search": true,
"deprecation_date": "2027-10-26"
},
"azure/eu/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.38e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
"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_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models"
},
"azure/gpt-5.5-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
@ -44436,11 +44689,11 @@
"cache_read_input_token_cost": 6e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1000000,
"max_tokens": 1000000,
"max_input_tokens": 1048576,
"max_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://docs.together.ai/docs/serverless-models",
"source": "https://api.together.xyz/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
@ -55573,6 +55826,73 @@
"supports_web_search": true,
"gemini_audio_only_live": true
},
"gemini-3.8-live": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true
},
"gemini-3.8-live-extended-thinking": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true,
"supports_reasoning": true
},
"gemini/gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
@ -55692,6 +56012,73 @@
"rpm": 10,
"gemini_audio_only_live": true
},
"gemini/gemini-3.8-live": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true
},
"gemini/gemini-3.8-live-extended-thinking": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_image_token": 1e-06,
"input_cost_per_token": 7.5e-07,
"input_cost_per_video_per_second": 3.3333333333333335e-05,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true,
"supports_reasoning": true
},
"gemini/gemini-3.1-flash-tts-preview": {
"input_cost_per_token": 1e-06,
"litellm_provider": "gemini",
@ -56850,6 +57237,38 @@
}
]
},
"volcengine/doubao-seed-2-1-pro-260628": {
"cache_read_input_token_cost": 1.725e-07,
"input_cost_per_token": 8.625e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 4.3125e-06,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-turbo-260628": {
"cache_read_input_token_cost": 8.625e-08,
"input_cost_per_token": 4.3125e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 2.15625e-06,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-0-lite-260215": {
"litellm_provider": "volcengine",
"max_input_tokens": 256000,