n8n: OpenAI credential with a custom Base URL

n8n's OpenAI credential has a Base URL field — point it at 666 AI and every OpenAI node, the AI Agent and embeddings can use any model we sell.

Replace YOUR-ENDPOINT with the endpoint shown on your API Key page after you sign up, and YOUR-KEY with your key. One key works for every model on 666 AI — Claude, GPT, Gemini, DeepSeek, Qwen and 200+ more.

1. Create the credential

  1. Credentials → New → OpenAI.
  2. API Key: YOUR-KEY.
  3. Base URL: https://YOUR-ENDPOINT/v1 (with /v1 — n8n tests the credential with GET …/models, which works on 666 AI).
  4. Save.

2. Use it in a workflow

  1. Add an AI Agent node and attach an OpenAI Chat Model sub-node, or use the OpenAI Chat Model on its own.
  2. Select the credential from step 1.
  3. Model: switch to By ID and type the exact ID, e.g. anthropic/claude-sonnet-5.5 or google/gemini-3.5-flash (the list mode shows all 600 IDs, which is long).
  4. Important: in the node, turn Use Responses API off when you use Claude models. Newer n8n versions turn it on by default, and on 666 AI Claude models are served only by chat completions.

Embeddings

The Embeddings OpenAI node uses the same credential; pick openai/text-embedding-3-small.

FAQ

The credential test fails

Check the Base URL ends with /v1 and the key has no spaces.

Error: model is not available on /v1/responses

Turn off Use Responses API in the OpenAI Chat Model node.

Create a free accountAll modelsDeveloper guides