API integrations
n8n with EasyAPI
Call EasyAPI from an n8n HTTP Request node. The downloadable workflow uses a manual trigger and a minimal Chat Completions request so you can inspect the endpoint and JSON directly.
Requirements
Keep API keys in server-side environment variables or n8n credentials. Exported workflows and shared code must contain no production secrets.
Setup steps
- Import the workflow into n8n. Create an HTTP Header Auth credential with name Authorization and value Bearer followed by your API key; select that credential on the HTTP Request node.
- Replace REPLACE_WITH_CATALOG_MODEL with a chat model from the catalog. The request uses POST, JSON content and the /v1/chat/completions endpoint.
- Run the manual trigger and inspect choices[0].message.content. Keep this first workflow non-streaming; add downstream nodes only after checking the returned JSON.
Runnable request
The examples use your selected public model. Model access and limits still depend on your API key and account group. deepseek-v4-pro-0813
curl https://token.easyapi.com/v1/chat/completions \
-H "Authorization: Bearer $EASYAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro-0813","messages":[{"role":"user","content":"Reply with one short greeting."}],"stream":false}'Download n8n workflowExpected result
A successful request returns a non-empty assistant message. Check the usage record and actual charge before increasing traffic.
Compatibility and limits
This guide covers text Chat Completions. Image, video, embeddings, tools and structured output require separate model and endpoint checks. OpenAI client compatibility does not guarantee every vendor feature.
Read API documentationQuestions and troubleshooting
- Is the exported workflow safe to share?
- The file contains neither a key nor a credential ID. n8n stores the selected Header Auth credential separately; inspect any later workflow exports before sharing them.
- Why use HTTP Request instead of an AI Agent node?
- HTTP Request makes the exact endpoint, body and response visible and does not assume tool-call support. An AI Agent or OpenAI Chat Model node is a separate setup with its own model and credential requirements.
- What should I check for 401, 404 or 429?
- For 401 check the selected credential and Bearer prefix. For 404 check the base URL, endpoint and model ID. For 429 inspect account limits and add bounded retries rather than an unbounded workflow loop.
Official sources
n8n · Checked