Power n8n workflows with
the best open-source models
Use Kyma as the LLM behind your n8n OpenAI, AI Agent, and Basic LLM Chain nodes. OpenAI-compatible, auto-failover, free to start. No OpenAI key needed.
Best Open Models
Qwen 3.6 Plus for quality, Gemma 4 31B for cheap high-volume runs, Kimi K2.6 for agentic tool use — pick per workflow with one key.
Auto-Failover
Multi-route redundancy behind one endpoint. If a route is slow, Kyma switches automatically — your scheduled workflows keep running.
OpenAI-Compatible
Drops straight into n8n's OpenAI credential. Just set the Base URL and paste your key — every OpenAI-style node uses Kyma.
Recommended Models for n8n
Ranked by quality, cost, and fit for automated workflows.
Alibaba's highest-quality all-rounder. 131K context with strong reasoning — the safe default for any n8n workflow.
qwen-3.6-plus131K context
Google's open model with the lowest cost per token. Ideal for high-volume automations that run thousands of times a day.
gemma-4-31bLowest cost
Moonshot's flagship. 262K context with the strongest agentic tool use — best for AI Agent nodes that call tools.
kimi-k2.6262K context
DeepSeek's fast, cheap V4 tier with a 1M context window. Great balance of speed, price, and quality for long inputs.
deepseek-v4-flash1M context
Setup in 30 Seconds
1. Get your free API key → 2. Create the credential below → 3. Drop it into any LLM node.
1. In n8n, open Credentials → New → search "OpenAI" 2. Create an "OpenAI account" credential and set: API Key: ky-xxxxx (get yours at kymaapi.com) Base URL: https://kymaapi.com/v1 3. Save. This credential now points every OpenAI-style node at Kyma instead of OpenAI. That's it — no OpenAI key required.
Add an OpenAI, AI Agent, or Basic LLM Chain node and: Credential: the Kyma "OpenAI account" you created Model: qwen-3.6-plus Note: the Model field is free-text. Type any Kyma model id directly — e.g. qwen-3.6-plus, gemma-4-31b, kimi-k2.6, or deepseek-v4-flash. No dropdown limit.
Pro Tips
Pick the right model per node to get the best results and lowest cost.
Use qwen-3.6-plus as your default for reliable quality across most workflows
Use gemma-4-31b on high-volume automations that run thousands of times a day to cut cost
Use kimi-k2.6 in AI Agent nodes that call tools for the strongest agentic behavior
Automate with n8n — free
$0.50 free credits on signup. No credit card required.
Get Free API KeyExplore more
Browse the recommended models for n8n and compare them against the rest of the catalog.