Linkrra Log in Sign up free

Guide · Flowise

Connect Flowise to Synap

3 steps · about 2 minutes

  1. Get a free key

    Sign in with Google at synap.linkrra.com — no card. Your key starts with sk-pool-.

  2. Add a ChatOpenAI Custom node

    Under Chat Models pick ChatOpenAI Custom — not plain ChatOpenAI, whose model list is fixed and has no Synap model in it. Its credential is the ordinary OpenAI API one: put your sk-pool- key there.

    Base Path    https://synap.linkrra.com/v1
Model Name   qwen3-coder-30b

  3. Wire it up and ask

    Feed it into a chain — a Conversation Chain with a Buffer Memory is enough — then chat in the editor, or call the flow over HTTP.

    curl http://localhost:3000/api/v1/prediction/<chatflow-id> \
  -H 'content-type: application/json' \
  -d '{"question":"Say OK and nothing else."}'
Notes, prices and limits

Two fields on one node: Base Path and Model Name. 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 the Flowise 3.0.13 Docker image: ChatOpenAI Custom with that Base Path, into a Conversation Chain with a Buffer Memory, answering through both the editor’s route and /api/v1/prediction. Pin a version you have tested — the latest tag did not start for us.

Everything else about the node is the OpenAI one: temperature, max tokens, streaming and tool calling are in the same places.

Flowise’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 Flowise docs, and the 3.0.13 Docker image run against this API, checked 2026-11-03 17:45 UTC. Prices refresh from /v1/models when this page loads.