docs: Add Moonshot Kimi public endpoint documentation#730
Conversation
Add a new Public Endpoints model page for Moonshot Kimi, a text/LLM family endpoint serving three variants (kimi-k2.6, kimi-k2.7-code, kimi-k3) selected via the model field, and wire it into the Models nav, the model reference table, and the Public Endpoints overview.
![promptless[bot]](https://avatars.githubusercontent.com/in/979718?s=60&v=4){kind=small}
|
|
||
| | | | | ||
| |---|---| | ||
| | **Endpoint** | `https://api.runpod.ai/v2/moonshot-kimi/runsync` | |
There was a problem hiding this comment.
Confirms API endpoint URL https://api.runpod.ai/v2/moonshot-kimi/runsync (single slug serves the whole Kimi family; variant selected via model field, not URL) as shown in the live Runpod console Hub playground for Moonshot Kimi.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| | | | | ||
| |---|---| | ||
| | **Endpoint** | `https://api.runpod.ai/v2/moonshot-kimi/runsync` | | ||
| | **Pricing** | \$4.00–\$15.00 per 1M tokens | |
There was a problem hiding this comment.
Confirms overall pricing range $4.00-$15.00 per 1M tokens across the Kimi variant family, as shown in the live Runpod console Hub playground for Moonshot Kimi.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
|
|
||
| | `model` value | Description | Context window | Price | | ||
| |---|---|---|---| | ||
| | `kimi-k2.6` (default) | General-purpose model with thinking and non-thinking modes, agentic capabilities, and multimodal input. | 256K (262,144 tokens) | \$4.00 per 1M tokens | |
There was a problem hiding this comment.
Confirms kimi-k2.6 variant details: default model, general-purpose with thinking/non-thinking modes, agentic, multimodal input, 256K (262,144-token) context, $4.00 per 1M tokens; from the live Runpod console Hub playground for Moonshot Kimi.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| | `model` value | Description | Context window | Price | | ||
| |---|---|---|---| | ||
| | `kimi-k2.6` (default) | General-purpose model with thinking and non-thinking modes, agentic capabilities, and multimodal input. | 256K (262,144 tokens) | \$4.00 per 1M tokens | | ||
| | `kimi-k2.7-code` | Coding-focused model with thinking mode and agentic capabilities. | 256K (262,144 tokens) | \$4.00 per 1M tokens | |
There was a problem hiding this comment.
Confirms kimi-k2.7-code variant details: coding-focused, thinking mode, agentic, 256K (262,144-token) context, $4.00 per 1M tokens; from the live Runpod console Hub playground for Moonshot Kimi.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| |---|---|---|---| | ||
| | `kimi-k2.6` (default) | General-purpose model with thinking and non-thinking modes, agentic capabilities, and multimodal input. | 256K (262,144 tokens) | \$4.00 per 1M tokens | | ||
| | `kimi-k2.7-code` | Coding-focused model with thinking mode and agentic capabilities. | 256K (262,144 tokens) | \$4.00 per 1M tokens | | ||
| | `kimi-k3` | Flagship model with always-on reasoning and configurable reasoning effort for long-horizon coding and knowledge work. | 1M (1,048,576 tokens) | \$15.00 per 1M tokens | |
There was a problem hiding this comment.
Confirms kimi-k3 variant details: flagship, always-on reasoning with configurable reasoning effort, long-horizon coding/knowledge, 1M (1,048,576-token) context, $15.00 per 1M tokens; from the live Runpod console Hub playground for Moonshot Kimi.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| ```python Python (OpenAI SDK) | ||
| from openai import OpenAI | ||
|
|
||
| client = OpenAI( |
There was a problem hiding this comment.
Confirms OpenAI-compatible base_url https://api.runpod.ai/v2/moonshot-kimi/openai/v1 for the Moonshot Kimi Public Endpoint family, verified via the live Runpod console Hub playground.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
|
Just a reminder: If you'd like me to act on any feedback you have via Github comments, just type @Promptless in your suggestion and I'll get right on it! (I won't show up in the user dropdown, but I'll process any request that has @Promptless in the comment body.) |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
1 participant
Open this suggestion in Promptless to view citations and reasoning process
Documents Moonshot Kimi as a new text Public Endpoint. Unlike existing single-model text endpoints, Moonshot Kimi is a family endpoint: a single slug (
moonshot-kimi) serves three variants—kimi-k2.6(default),kimi-k2.7-code, andkimi-k3—that you select with themodelfield in the request body, each with its own context window and price.A new model page covers the endpoint URL, the three variants and how to select them, native request/response parameters, OpenAI-compatible usage (including streaming), and tiered cost calculation ($4.00 per 1M tokens for Kimi K2.6 and K2.7 Code; $15.00 per 1M tokens for Kimi K3). The page is wired into the Models navigation, the model reference table, and the Public Endpoints overview so the model is discoverable alongside the other text models.
Files touched:
public-endpoints/models/moonshot-kimi.mdx(new),docs.json,public-endpoints/reference.mdx,public-endpoints/overview.mdx.Trigger Events
Tip: Filter the Dashboard by labels or assignees to focus on what matters to you 🔎