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] 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",