From liter-llm
Covers running the `liter-llm api` OpenAI-compatible gateway with virtual keys, per-key rate limits, budgets, cost tracking, model routing, and its TOML configuration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/liter-llm:running-the-proxyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`liter-llm api` is a drop-in OpenAI-compatible gateway: 22 REST endpoints that
liter-llm api is a drop-in OpenAI-compatible gateway: 22 REST endpoints that
route to 143 providers, with multi-tenant virtual keys, rate limits, budgets,
and cost tracking.
liter-llm api --config liter-llm-proxy.toml
The proxy auto-discovers liter-llm-proxy.toml in the current directory.
[server]
host = "0.0.0.0"
port = 4000
[auth]
master_key = "${LITER_LLM_MASTER_KEY}"
[[virtual_keys]]
key = "sk-team-frontend"
models = ["openai/*", "anthropic/*"]
rpm = 60
tpm = 100000
budget = 50.0
[[providers]]
name = "openai"
api_key = "${OPENAI_API_KEY}"
[[providers]]
name = "anthropic"
api_key = "${ANTHROPIC_API_KEY}"
${ENV_VAR} interpolation keeps secrets out of the file.
curl http://localhost:4000/v1/chat/completions \
-H "Authorization: Bearer sk-team-frontend" \
-d '{"model": "openai/gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
master_key administers them./openapi.json.docker run -p 4000:4000 -e LITER_LLM_MASTER_KEY=sk-key ghcr.io/xberg-io/liter-llm.npx claudepluginhub xberg-io/plugins --plugin liter-llmCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.