scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 91

chore(prices): sync Baseten prices: 12 models, 9 new [enrichment failed: Baseten, 15 held] (#42558)

Browse source 
baseten/deepseek-ai/DeepSeek-V4.1-Flash: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/moonshotai/Kimi-K2.6: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/moonshotai/Kimi-K2.7-Code: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/moonshotai/Kimi-K3: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/openai/gpt-oss-120b: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, cache_read_input_token_cost
baseten/thinkingmachines/inkling: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/thinkingmachines/inkling-small: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/zai-org/GLM-4.7: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, cache_read_input_token_cost
baseten/zai-org/GLM-5.2: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
baseten/zai-org/GLM-5.3: supports_reasoning
baseten/zai-org/GLM-5.3-Flash: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
This commit is contained in:
berriai-litellm-provider-info-sync[bot] 2026-09-22 13:24:49 -07:00 • committed by GitHub
parent e841f32e50
commit 2727359a9e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 358 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

182
litellm/model_prices_and_context_window_backup.json
View file

@ -31722,10 +31722,21 @@
"output_cost_per_token": 3.15e-06
},
"baseten/zai-org/GLM-4.7": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "baseten",
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"output_cost_per_token": 2.2e-06
"output_cost_per_token": 2.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": false,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"baseten/zai-org/GLM-4.6": {
"input_cost_per_token": 6e-07,
@ -31752,10 +31763,21 @@
"output_cost_per_token": 2.5e-06
},
"baseten/openai/gpt-oss-120b": {
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "baseten",
"max_input_tokens": 128072,
"max_output_tokens": 128072,
"max_tokens": 128072,
"mode": "chat",
"output_cost_per_token": 5e-07
"output_cost_per_token": 5e-07,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"baseten/deepseek-ai/DeepSeek-V3.1": {
"input_cost_per_token": 5e-07,
@ -68322,7 +68344,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://www.baseten.co/pricing/",
"source": "https://inference.baseten.co/v1/models",
"supported_modalities": [
"text",
"image"
@ -68332,6 +68354,7 @@
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
@ -77489,5 +77512,158 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": false
},
"baseten/deepseek-ai/DeepSeek-V4.1-Flash": {
"cache_read_input_token_cost": 7e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/moonshotai/Kimi-K2.6": {
"cache_read_input_token_cost": 1.6e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/moonshotai/Kimi-K2.7-Code": {
"cache_read_input_token_cost": 1.6e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/moonshotai/Kimi-K3": {
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "baseten",
"max_input_tokens": 202800,
"max_output_tokens": 202800,
"max_tokens": 202800,
"mode": "chat",
"output_cost_per_token": 2.4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"baseten/thinkingmachines/inkling": {
"cache_read_input_token_cost": 1.7e-07,
"input_cost_per_token": 1e-06,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4.05e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/thinkingmachines/inkling-small": {
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/zai-org/GLM-5.2": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/zai-org/GLM-5.3-Flash": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
}
}

182
model_prices_and_context_window.json
View file

@ -31722,10 +31722,21 @@
"output_cost_per_token": 3.15e-06
},
"baseten/zai-org/GLM-4.7": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "baseten",
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"output_cost_per_token": 2.2e-06
"output_cost_per_token": 2.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": false,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"baseten/zai-org/GLM-4.6": {
"input_cost_per_token": 6e-07,
@ -31752,10 +31763,21 @@
"output_cost_per_token": 2.5e-06
},
"baseten/openai/gpt-oss-120b": {
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "baseten",
"max_input_tokens": 128072,
"max_output_tokens": 128072,
"max_tokens": 128072,
"mode": "chat",
"output_cost_per_token": 5e-07
"output_cost_per_token": 5e-07,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"baseten/deepseek-ai/DeepSeek-V3.1": {
"input_cost_per_token": 5e-07,
@ -68322,7 +68344,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://www.baseten.co/pricing/",
"source": "https://inference.baseten.co/v1/models",
"supported_modalities": [
"text",
"image"
@ -68332,6 +68354,7 @@
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
@ -77489,5 +77512,158 @@
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": false
},
"baseten/deepseek-ai/DeepSeek-V4.1-Flash": {
"cache_read_input_token_cost": 7e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/moonshotai/Kimi-K2.6": {
"cache_read_input_token_cost": 1.6e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/moonshotai/Kimi-K2.7-Code": {
"cache_read_input_token_cost": 1.6e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/moonshotai/Kimi-K3": {
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "baseten",
"max_input_tokens": 202800,
"max_output_tokens": 202800,
"max_tokens": 202800,
"mode": "chat",
"output_cost_per_token": 2.4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"baseten/thinkingmachines/inkling": {
"cache_read_input_token_cost": 1.7e-07,
"input_cost_per_token": 1e-06,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4.05e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/thinkingmachines/inkling-small": {
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/zai-org/GLM-5.2": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/zai-org/GLM-5.3-Flash": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
}
}