Gitpulse
Merged
Size
L
Change Breakdown
Feature90%
Config10%
#28156feat(Moonshot Kimi Chat Model Node): Add Moonshot Kimi Chat Model sub-node

Moonshot AI models now available in n8n

Moonshot AI models now available in n8n
DA
DawidMyslak
·Apr 9, 2026

n8n's LangChain integration now supports Moonshot AI's Kimi language models, letting workflow builders connect to another OpenAI-compatible API provider directly from the canvas.

Moonshot AI's Kimi models are now available as a native sub-node in n8n's LangChain integration. Workflow builders can authenticate with an API key from platform.kimi.ai, select from available models (defaulting to kimi-k2.5), and configure parameters like temperature, max tokens, and response format — all without leaving the n8n editor.

The integration follows the same OpenAI-compatible pattern as existing DeepSeek and xAI Grok nodes, using ChatOpenAI with a custom base URL. A region selector accommodates both international and mainland China endpoints. The new node works with AI Agent and AI Chain root nodes, and standard configuration options like frequency/presence penalties, top-p sampling, and timeout controls are all exposed.

This expands the roster of supported LLM providers in n8n, giving automation builders more flexibility when integrating language models into their workflows. The Moonshot node is registered in the Agent V1 allowlist and includes tracing support for observability.

The addition lives in the @n8n/nodes-langchain package, alongside other chat model integrations.

View Original GitHub Description

Summary

Adds a new Moonshot Kimi Chat Model LangChain sub-node for connecting to the Moonshot AI platform via its OpenAI-compatible API.

2026-04-08 09 36 58

What's included

  • MoonshotApi credential – API key authentication against https://api.moonshot.ai/v1
  • LmChatMoonshot node – Chat model sub-node using ChatOpenAI with custom base URL (same pattern as DeepSeek/xAI Grok)
    • Dynamic model loading via GET /models
    • Default model: kimi-k2.5
    • Options: temperature, top-p, frequency/presence penalty, max tokens, response format (text/JSON), timeout, retries
  • Light/dark mode icons from official Moonshot AI branding
  • Agent V1 allowlist entries for conversational and tools agents
  • Unit tests covering node description, supplyData, options, proxy agent, and tracing

How to test

  1. Go to Settings → Credentials → Add Credential → Moonshot
  2. Enter an API key from platform.kimi.ai/console/api-keys
  3. Test the credential — should succeed
  4. Create a workflow with an AI Agent node, attach the Moonshot Kimi Chat Model sub-node
  5. Verify the model dropdown loads available models (e.g. kimi-k2.5)
  6. Send a test message through the agent

Related Linear tickets, Github issues, and Community forum posts

https://linear.app/n8n/issue/NODE-4772

Review / Merge checklist

  • PR title and summary are descriptive. (conventions)
  • Docs updated or follow-up ticket created.
  • Tests included.
  • PR Labeled with release/backport (if the PR is an urgent fix that needs to be backported)

Made with Cursor

© 2026 · via Gitpulse