From ef1cde433ea7c6dd1515de06c6d0d748fae4a197 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Thu, 20 Aug 2026 18:22:14 -0700 Subject: [PATCH 1/3] fix: add moonshot/kimi-k3 to the cost map models.litellm.ai and released litellm versions read model_prices_and_context_window.json from main at runtime, so Kimi K3 is missing from the hosted catalog even though the entry is in review for litellm_internal_staging in #37552. This copies that entry onto main so the catalog picks it up on its next fetch. Data only: the cost map and its backup copy, no code changes. Pricing matches Moonshot's published rates ($3/M input, $0.30/M cache read, $15/M output, 1,048,576-token context). The fireworks_ai and Azure Foundry kimi-k3 variants are separate work in #37512 and #37658; neither touches the native moonshot/kimi-k3 key. --- .../model_prices_and_context_window_backup.json | 17 +++++++++++++++++ model_prices_and_context_window.json | 17 +++++++++++++++++ 2 files changed, 34 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 07f9027313b..53d069c4a71 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -30025,6 +30025,23 @@ "supports_video_input": true, "supports_vision": true }, + "moonshot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://platform.kimi.ai/docs/pricing/chat-k3", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, "moonshot/kimi-latest": { "cache_read_input_token_cost": 1.5e-07, "deprecation_date": "2026-01-28", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 07f9027313b..53d069c4a71 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -30025,6 +30025,23 @@ "supports_video_input": true, "supports_vision": true }, + "moonshot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://platform.kimi.ai/docs/pricing/chat-k3", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, "moonshot/kimi-latest": { "cache_read_input_token_cost": 1.5e-07, "deprecation_date": "2026-01-28", From a945a03132c0fdc5a14e3a6ea48cd2d0cc1cc278 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=B4=94=E6=B6=A3?= Date: Wed, 26 Aug 2026 09:37:47 +0800 Subject: [PATCH 2/3] feat: add Synthorai OpenAI-compatible provider --- litellm/llms/openai_like/providers.json | 40 ++++++++++++++++++++----- 1 file changed, 33 insertions(+), 7 deletions(-) diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json index a458a209ea9..4fc94b32388 100644 --- a/litellm/llms/openai_like/providers.json +++ b/litellm/llms/openai_like/providers.json @@ -130,7 +130,10 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"] + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] }, "tensormesh": { "base_url": "https://serverless.tensormesh.ai/v1", @@ -140,13 +143,19 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"] + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] }, "parasail": { "base_url": "https://api.parasail.io/v1", "api_key_env": "PARASAIL_API_KEY", "api_base_env": "PARASAIL_API_BASE", - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "special_handling": { "force_store_false": true } @@ -166,14 +175,21 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"] + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] }, "meta": { "base_url": "https://api.meta.ai/v1", "api_key_env": "META_API_KEY", "api_base_env": "META_API_BASE", "base_class": "openai_gpt", - "supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/messages"] + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ] }, "cognition": { "base_url": "https://api.cognition.ai/v1", @@ -187,7 +203,11 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/embeddings"] + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/embeddings" + ] }, "scx-ai": { "base_url": "https://api.scx.ai/v1", @@ -199,6 +219,12 @@ "constraints": { "temperature_max": 1.99 }, - "supported_endpoints": ["/v1/chat/completions"] + "supported_endpoints": [ + "/v1/chat/completions" + ] + }, + "synthorai": { + "base_url": "https://synthorai.io/v1", + "api_key_env": "SYNTHORAI_API_KEY" } } From 6fe9718c113e6d65f0d280f8c04be8567af70fd7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=B4=94=E6=B6=A3?= Date: Wed, 26 Aug 2026 10:51:36 +0800 Subject: [PATCH 3/3] chore: keep the diff to the added entry only (no reformatting) --- litellm/llms/openai_like/providers.json | 36 +++++-------------------- 1 file changed, 7 insertions(+), 29 deletions(-) diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json index 4fc94b32388..8be695257c2 100644 --- a/litellm/llms/openai_like/providers.json +++ b/litellm/llms/openai_like/providers.json @@ -130,10 +130,7 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ] + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"] }, "tensormesh": { "base_url": "https://serverless.tensormesh.ai/v1", @@ -143,19 +140,13 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ] + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"] }, "parasail": { "base_url": "https://api.parasail.io/v1", "api_key_env": "PARASAIL_API_KEY", "api_base_env": "PARASAIL_API_BASE", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], "special_handling": { "force_store_false": true } @@ -175,21 +166,14 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ] + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"] }, "meta": { "base_url": "https://api.meta.ai/v1", "api_key_env": "META_API_KEY", "api_base_env": "META_API_BASE", "base_class": "openai_gpt", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/messages" - ] + "supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/messages"] }, "cognition": { "base_url": "https://api.cognition.ai/v1", @@ -203,11 +187,7 @@ "param_mappings": { "max_completion_tokens": "max_tokens" }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/embeddings" - ] + "supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/embeddings"] }, "scx-ai": { "base_url": "https://api.scx.ai/v1", @@ -219,9 +199,7 @@ "constraints": { "temperature_max": 1.99 }, - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supported_endpoints": ["/v1/chat/completions"] }, "synthorai": { "base_url": "https://synthorai.io/v1",