From d1426748c19cf83886df98d42861526b6a984862 Mon Sep 17 00:00:00 2001 From: Kunal Das Date: Mon, 2 Nov 2026 09:40:37 +0000 Subject: [PATCH] fix(pricing): add kimchi model costs and request-level test --- ...odel_prices_and_context_window_backup.json | 131 ++++++++++++++++++ .../provider_create_fields.json | 7 +- model_prices_and_context_window.json | 131 ++++++++++++++++++ 3 files changed, 264 insertions(+), 5 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d68eb3ce775..9db14d628a1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -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, diff --git a/litellm/proxy/public_endpoints/provider_create_fields.json b/litellm/proxy/public_endpoints/provider_create_fields.json index 8b4d8ab71d4..d42ca60ce97 100644 --- a/litellm/proxy/public_endpoints/provider_create_fields.json +++ b/litellm/proxy/public_endpoints/provider_create_fields.json @@ -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" }, { diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d68eb3ce775..9db14d628a1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -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,