Schema | freellmpool

freellmpool

Describes the environment variables required to run the server.

Name	Required	Description
`GROQ_API_KEY`	No	Provider credential, shown in the Docker example as `--env GROQ_API_KEY`. Required only to unlock that provider's models and higher limits; the server can start credential-free while an enabled keyless route (e.g. Pollinations, OVHcloud, Kilo Gateway, LLM7) is available. Additional providers are configured with `freellmpool keys add <name>` or in `providers.toml`.
`FREELLMPOOL_MODE`	No	Conservative quota mode. `wise` makes `ask` default to a smaller output budget and spread routing, narrows `tokenmax` fan-out, and requires confirmation (or `--yes`) for broad multi-model calls. Per-command `--mode normal\|wise` overrides this. Defaults to normal behavior.
`FREELLMPOOL_ROUTING`	No	Routing strategy, e.g. `fast` to prefer the lowest-latency provider instead of the default least-used-first.
`FREELLMPOOL_PROXY_KEY`	No	Bearer token that clients must present when the proxy is deliberately exposed beyond loopback; Tailnet/LAN serving requires a real proxy bearer token by default. On loopback any placeholder key works unless this is set.
`FREELLMPOOL_PUBLIC_BADGE`	No	Set to `1` to make the proxy serve `/badge.svg` and `/summary.svg` live as public, embeddable badges.

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

ActivityMaintained

ResponsivenessResponsive