Guide · n8n
Connect n8n to Synap
-
Get a free key
Sign in with Google at synap.linkrra.com — no card. Your key starts with
sk-pool-. -
Create an OpenAI credential
Credentials → New → OpenAI. Paste your key, then fill the Base URL field. n8n runs its own connection test on save.
API Key sk-pool-... Base URL https://synap.linkrra.com/v1 -
Add an OpenAI node
OpenAI → Text → Message a model, with that credential. The Model dropdown fills itself from our catalogue.
Model qwen3-coder-30b -
Run it
Everything downstream is unchanged — the node returns the same shape as before.
{ "role": "assistant", "content": "N8N_SYNAP_OK" }
Notes, prices and limits
The built-in OpenAI credential, with a Base URL. Recommended model: qwen3-coder-30b —
$0.0675 in and $0.27 out
per 1M tokens, 98,304-token context.
Run live against this API on n8n 2.46.4: the credential’s own connection test returned {"status":"OK","message":"Connection successful!"}, the Model dropdown populated from our catalogue, and the workflow executed with status success.
No community node and no self-hosting requirement — the built-in OpenAI credential has a Base URL field, so this works the same on n8n Cloud.
Every node that takes an OpenAI credential takes this one, including the OpenAI Chat Model node inside an AI Agent.
n8n’s embeddings nodes need an embeddings endpoint, and Synap has none — it serves chat models. Point an embeddings node at another provider and keep the chat model here.
On the free tier: every request counts input and output against 100,000 free tokens a day, and answers stop at 4,096 output tokens. Coding agents send long prompts, so the free tier covers a short session; credits cover the rest.
Field names from n8n docs: OpenAI credentials, and n8n 2.46.4 run against this API, checked 2026-11-03 20:20 UTC. Prices refresh from /v1/models when this page loads.