scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83

fix(model-prices): migrate 38 models from legacy max_tokens to max_input_tokens/max_output_tokens

Browse source 
Models using only the legacy max_tokens field now have proper
max_input_tokens and max_output_tokens based on provider documentation.

Providers updated: OpenRouter (13), Gradient AI (13), Heroku (4),
Aleph Alpha (6), Together AI (2).
This commit is contained in:
Chesars 2026-03-23 12:25:12 -03:00
parent f5194b5ce3
commit 7bf311eb97
1 changed files with 109 additions and 104 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

213
model_prices_and_context_window.json
View file

@ -14604,17 +14604,14 @@
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
@ -14631,18 +14628,6 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
"gemini/gemini-embedding-001": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "gemini",
@ -19656,7 +19641,7 @@
},
"gradient_ai/alibaba-qwen3-32b": {
"litellm_provider": "gradient_ai",
"max_tokens": 2048,
"max_tokens": 40960,
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions"
@ -19664,7 +19649,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 131072,
"max_output_tokens": 40960
},
"gradient_ai/anthropic-claude-3-opus": {
"input_cost_per_token": 1.5e-05,
@ -19678,7 +19665,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 200000,
"max_output_tokens": 1024
},
"gradient_ai/anthropic-claude-3.5-haiku": {
"input_cost_per_token": 8e-07,
@ -19692,7 +19681,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 200000,
"max_output_tokens": 1024
},
"gradient_ai/anthropic-claude-3.5-sonnet": {
"input_cost_per_token": 3e-06,
@ -19706,7 +19697,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 200000,
"max_output_tokens": 1024
},
"gradient_ai/anthropic-claude-3.7-sonnet": {
"input_cost_per_token": 3e-06,
@ -19720,7 +19713,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 200000,
"max_output_tokens": 1024
},
"gradient_ai/deepseek-r1-distill-llama-70b": {
"input_cost_per_token": 9.9e-07,
@ -19734,7 +19729,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 32768,
"max_output_tokens": 8000
},
"gradient_ai/llama3-8b-instruct": {
"input_cost_per_token": 2e-07,
@ -19748,7 +19745,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 8192,
"max_output_tokens": 512
},
"gradient_ai/llama3.3-70b-instruct": {
"input_cost_per_token": 6.5e-07,
@ -19762,7 +19761,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 128000,
"max_output_tokens": 2048
},
"gradient_ai/mistral-nemo-instruct-2407": {
"input_cost_per_token": 3e-07,
@ -19776,7 +19777,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 128000,
"max_output_tokens": 512
},
"gradient_ai/openai-gpt-4o": {
"litellm_provider": "gradient_ai",
@ -19788,7 +19791,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 128000,
"max_output_tokens": 16384
},
"gradient_ai/openai-gpt-4o-mini": {
"litellm_provider": "gradient_ai",
@ -19800,7 +19805,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 128000,
"max_output_tokens": 16384
},
"gradient_ai/openai-o3": {
"input_cost_per_token": 2e-06,
@ -19814,7 +19821,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 200000,
"max_output_tokens": 100000
},
"gradient_ai/openai-o3-mini": {
"input_cost_per_token": 1.1e-06,
@ -19828,7 +19837,9 @@
"supported_modalities": [
"text"
],
"supports_tool_choice": false
"supports_tool_choice": false,
"max_input_tokens": 200000,
"max_output_tokens": 100000
},
"lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": {
"input_cost_per_token": 0,
@ -20128,11 +20139,13 @@
},
"heroku/claude-3-5-haiku": {
"litellm_provider": "heroku",
"max_tokens": 4096,
"max_tokens": 8192,
"mode": "chat",
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 200000,
"max_output_tokens": 8192
},
"heroku/claude-3-5-sonnet-latest": {
"litellm_provider": "heroku",
@ -20140,7 +20153,9 @@
"mode": "chat",
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 200000,
"max_output_tokens": 8192
},
"heroku/claude-3-7-sonnet": {
"litellm_provider": "heroku",
@ -20148,7 +20163,9 @@
"mode": "chat",
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 200000,
"max_output_tokens": 8192
},
"heroku/claude-4-sonnet": {
"litellm_provider": "heroku",
@ -20156,7 +20173,9 @@
"mode": "chat",
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 200000,
"max_output_tokens": 8192
},
"high/1024-x-1024/gpt-image-1": {
"input_cost_per_image": 0.167,
@ -20870,48 +20889,6 @@
"/v1/images/generations"
]
},
"luminous-base": {
"input_cost_per_token": 3e-05,
"litellm_provider": "aleph_alpha",
"max_tokens": 2048,
"mode": "completion",
"output_cost_per_token": 3.3e-05
},
"luminous-base-control": {
"input_cost_per_token": 3.75e-05,
"litellm_provider": "aleph_alpha",
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 4.125e-05
},
"luminous-extended": {
"input_cost_per_token": 4.5e-05,
"litellm_provider": "aleph_alpha",
"max_tokens": 2048,
"mode": "completion",
"output_cost_per_token": 4.95e-05
},
"luminous-extended-control": {
"input_cost_per_token": 5.625e-05,
"litellm_provider": "aleph_alpha",
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 6.1875e-05
},
"luminous-supreme": {
"input_cost_per_token": 0.000175,
"litellm_provider": "aleph_alpha",
"max_tokens": 2048,
"mode": "completion",
"output_cost_per_token": 0.0001925
},
"luminous-supreme-control": {
"input_cost_per_token": 0.00021875,
"litellm_provider": "aleph_alpha",
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 0.000240625
},
"max-x-max/50-steps/stability.stable-diffusion-xl-v0": {
"litellm_provider": "bedrock",
"max_input_tokens": 77,
@ -24048,12 +24025,14 @@
"input_cost_per_image": 0.0004,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "openrouter",
"max_tokens": 200000,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"max_input_tokens": 200000,
"max_output_tokens": 4096
},
"openrouter/anthropic/claude-3.5-sonnet": {
"input_cost_per_token": 3e-06,
@ -24570,18 +24549,22 @@
"openrouter/mancer/weaver": {
"input_cost_per_token": 5.625e-06,
"litellm_provider": "openrouter",
"max_tokens": 8000,
"max_tokens": 2000,
"mode": "chat",
"output_cost_per_token": 5.625e-06,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 8000,
"max_output_tokens": 2000
},
"openrouter/meta-llama/llama-3-70b-instruct": {
"input_cost_per_token": 5.9e-07,
"litellm_provider": "openrouter",
"max_tokens": 8192,
"max_tokens": 8000,
"mode": "chat",
"output_cost_per_token": 7.9e-07,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 8192,
"max_output_tokens": 8000
},
"openrouter/minimax/minimax-m2": {
"input_cost_per_token": 2.55e-07,
@ -24669,34 +24652,42 @@
"openrouter/mistralai/mistral-7b-instruct": {
"input_cost_per_token": 1.3e-07,
"litellm_provider": "openrouter",
"max_tokens": 8192,
"max_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 1.3e-07,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 32768,
"max_output_tokens": 8191
},
"openrouter/mistralai/mistral-large": {
"input_cost_per_token": 8e-06,
"litellm_provider": "openrouter",
"max_tokens": 32000,
"max_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 2.4e-05,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 128000,
"max_output_tokens": 8191
},
"openrouter/mistralai/mistral-small-3.1-24b-instruct": {
"input_cost_per_token": 1e-07,
"litellm_provider": "openrouter",
"max_tokens": 32000,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3e-07,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 131072,
"max_output_tokens": 131072
},
"openrouter/mistralai/mistral-small-3.2-24b-instruct": {
"input_cost_per_token": 1e-07,
"litellm_provider": "openrouter",
"max_tokens": 32000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 128000,
"max_output_tokens": 128000
},
"openrouter/mistralai/mixtral-8x22b-instruct": {
"input_cost_per_token": 6.5e-07,
@ -24704,7 +24695,9 @@
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 6.5e-07,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 65536,
"max_output_tokens": 65536
},
"openrouter/moonshotai/kimi-k2.5": {
"cache_read_input_token_cost": 1e-07,
@ -24724,26 +24717,32 @@
"openrouter/openai/gpt-3.5-turbo": {
"input_cost_per_token": 1.5e-06,
"litellm_provider": "openrouter",
"max_tokens": 4095,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 2e-06,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 16385,
"max_output_tokens": 4096
},
"openrouter/openai/gpt-3.5-turbo-16k": {
"input_cost_per_token": 3e-06,
"litellm_provider": "openrouter",
"max_tokens": 16383,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-06,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 16385,
"max_output_tokens": 4096
},
"openrouter/openai/gpt-4": {
"input_cost_per_token": 3e-05,
"litellm_provider": "openrouter",
"max_tokens": 8192,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-05,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 8191,
"max_output_tokens": 4096
},
"openrouter/openai/gpt-4.1": {
"cache_read_input_token_cost": 5e-07,
@ -25251,10 +25250,12 @@
"openrouter/undi95/remm-slerp-l2-13b": {
"input_cost_per_token": 1.875e-06,
"litellm_provider": "openrouter",
"max_tokens": 6144,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.875e-06,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 6144,
"max_output_tokens": 4096
},
"openrouter/x-ai/grok-4": {
"input_cost_per_token": 3e-06,
@ -27862,14 +27863,16 @@
"together_ai/deepseek-ai/DeepSeek-V3.1": {
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
"max_tokens": 128000,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1.7e-06,
"source": "https://www.together.ai/models/deepseek-v3-1",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"max_input_tokens": 128000,
"max_output_tokens": 16384
},
"together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": {
"litellm_provider": "together_ai",
@ -31147,7 +31150,9 @@
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models",
"supported_regions": ["global"],
"supported_regions": [
"global"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,