Schema | io.github.0xzr/freellmpool

io.github.0xzr/freellmpool

Describes the environment variables required to run the server.

Name	Required	Description
`GROQ_API_KEY`	No	Provider credential example passed to the container (`--env GROQ_API_KEY`). Keys for other providers unlock more models and higher limits; add them with `freellmpool keys add <provider>`. Omitting provider keys allows a credential-free start, where the proxy can answer only while an enabled keyless route is available (e.g. Pollinations, OVHcloud, Kilo Gateway, LLM7).
`FREELLMPOOL_MODE`	No	Conservative quota mode, e.g. `wise`: `ask` defaults to a smaller output budget and spread routing, `tokenmax` narrows its default fan-out, and broad multi-model calls require confirmation unless `--yes` is passed. Overridden per-command by `--mode normal\|wise` or by `[settings] mode = "wise"` in config.toml.
`FREELLMPOOL_ROUTING`	No	Routing strategy for the pool; set to `fast` to prefer the lowest-latency provider instead of the default least-used-first.
`FREELLMPOOL_PROXY_KEY`	No	Bearer token required from clients when the proxy is deliberately exposed beyond loopback. Set this instead of passing `--api-key`; Tailnet/LAN serving requires a real proxy bearer token by default.
`FREELLMPOOL_PUBLIC_BADGE`	No	Set to `1` to let the proxy serve `/badge.svg` and `/summary.svg` live so public badges are embeddable.

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityActive

ResponsivenessResponsive