tool

FreeLLMAPI

Routes bounded agent requests through one OpenAI-compatible API across the free-tier providers and custom endpoints you configure.

What it provides

OpenAI-compatibleProvider routingExperimental

Connect an HTTPS API gateway with an optional scoped token. The installed client supports discovery and bounded HTTP calls.

Connection requirements

Run a pinned FreeLLMAPI release outside the bot, keep its port bound to loopback, and publish it through an HTTPS reverse proxy. Do not deploy the upstream `:latest` tag. Copy the `freellmapi-…` unified API key from its Keys page, keep Bearer selected, and paste that key below. Connect the server origin, not a `/v1` suffix. Provider keys are encrypted and remain on the FreeLLMAPI host; the bot only holds the unified key. Upstream explicitly positions this as a single-user service for personal experimentation, not a stable production inference substrate, and provider quotas or terms can change, so do not rely on the advertised free-token total or an SLA.

Protocol
OpenAI-compatible REST
Endpoint
https://freellmapi.example.com
Authentication
bearer
Example callsget /v1/modelspost /v1/chat/completions {"model":"auto","messages":[{"role":"user","content":"Hello"}]}
Open official setup guide ↗

Where to add it

Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.

Related Models & routing