scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-10 08:28:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

fix(pricing): add kimchi model costs and request-level test

Browse source
This commit is contained in:
Kunal Das 2026-11-02 09:40:37 +00:00
parent 2b6437a3d7
commit d1426748c1
3 changed files with 264 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

131
litellm/model_prices_and_context_window_backup.json
View file

@ -63165,6 +63165,137 @@
"supports_prompt_caching": true,
"source": "https://docs.devin.ai/desktop/models"
},
"kimchi/kimi-k3": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"cache_read_input_token_cost": 3e-07,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/kimi-k2.7": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 9.5e-07,
"output_cost_per_token": 4e-06,
"cache_read_input_token_cost": 1.9e-07,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/nemotron-3-ultra-fp4": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 3.6e-06,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_native_streaming": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/deepseek-v4-flash": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 2.8e-07,
"cache_read_input_token_cost": 7e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_native_streaming": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/deepseek-v4-flash-0731": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 2.8e-07,
"cache_read_input_token_cost": 7e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_native_streaming": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/deepseek-v4.1-flash": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 6e-09,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_native_streaming": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/glm-5.3": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"cache_read_input_token_cost": 2.6e-07,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/glm-5.3-flash": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 5e-07,
"cache_read_input_token_cost": 3e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/minimax-m3": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 6e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"pinstripes/ps/glm-4.5-air": {
"max_input_tokens": 128000,
"max_output_tokens": 128000,

7
litellm/proxy/public_endpoints/provider_create_fields.json
View file

@ -488,7 +488,7 @@
"key": "api_base",
"label": "Upstream API Base",
"placeholder": "https://api.anthropic.com",
"tooltip": "Optional. Where the proxy forwards requests upstream. Leave blank to use Anthropic's public API. Set this only for private Anthropic deployments or reverse proxies. Do NOT set this to your LiteLLM proxy URL \u2014 that causes a recursive loop.",
"tooltip": "Optional. Where the proxy forwards requests upstream. Leave blank to use Anthropic's public API. Set this only for private Anthropic deployments or reverse proxies. Do NOT set this to your LiteLLM proxy URL — that causes a recursive loop.",
"required": false,
"field_type": "text",
"options": null,
@ -2455,10 +2455,7 @@
"tooltip": "jwt_bearer_obo: on-behalf-of with the JWT bearer grant (Microsoft Entra). rfc8693: standard OAuth 2.0 token exchange.",
"required": false,
"field_type": "select",
"options": [
"jwt_bearer_obo",
"rfc8693"
],
"options": ["jwt_bearer_obo", "rfc8693"],
"default_value": "jwt_bearer_obo"
},
{

131
model_prices_and_context_window.json
View file

@ -63165,6 +63165,137 @@
"supports_prompt_caching": true,
"source": "https://docs.devin.ai/desktop/models"
},
"kimchi/kimi-k3": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"cache_read_input_token_cost": 3e-07,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/kimi-k2.7": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 9.5e-07,
"output_cost_per_token": 4e-06,
"cache_read_input_token_cost": 1.9e-07,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/nemotron-3-ultra-fp4": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 3.6e-06,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_native_streaming": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/deepseek-v4-flash": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 2.8e-07,
"cache_read_input_token_cost": 7e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_native_streaming": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/deepseek-v4-flash-0731": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 2.8e-07,
"cache_read_input_token_cost": 7e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_native_streaming": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/deepseek-v4.1-flash": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 6e-09,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_native_streaming": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/glm-5.3": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"cache_read_input_token_cost": 2.6e-07,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/glm-5.3-flash": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 5e-07,
"cache_read_input_token_cost": 3e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"kimchi/minimax-m3": {
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 6e-08,
"litellm_provider": "kimchi",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.kimchi.dev/docs/model-apis-pricing"
},
"pinstripes/ps/glm-4.5-air": {
"max_input_tokens": 128000,
"max_output_tokens": 128000,