For n8n

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, pay per use. 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

For eligible failures, Kyma API tries another compatible route when available. Requests can still fail.

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.

1
Qwen 3.6 PlusVision input

Supports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.

qwen-3.6-plus

Reasoning

2
Gemma 4 31BVision input

Supports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.

gemma-4-31b

Reasoning

3
Kimi K2.6Vision input

Supports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.

kimi-k2.6

Reasoning

4
DeepSeek V4 FlashTool use

Supports reasoning, tool use. Compare current prices and measured uptime on the model page.

deepseek-v4-flash

Reasoning

Setup guide

1. Create account2. Create the credential below 3. Drop it into any LLM node.

🔑n8n: OpenAI Credential
1. In n8n, open Credentials → New → search "OpenAI"

2. Create an "OpenAI account" credential and set:
   API Key:    kyma-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.
🤖Use it in a node
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 balance output quality and cost for your workload.

1

Use qwen-3.6-plus as your default for reliable quality across most workflows

2

Use gemma-4-31b on high-volume automations that run thousands of times a day to cut cost

3

Use kimi-k2.6 in AI Agent nodes that call tools for tool-use workflows

Connect n8n to Kyma API

$0.50 signup credit for eligible free-tier models after email verification. No card required.

Create account

Explore more

Browse the recommended models for n8n and compare them against the rest of the catalog.