Self-hosted chat UI
How to use LibreChat with Rapid Router
LibreChat supports custom endpoints in librechat.yaml. One block adds Rapid Router with its own name in the endpoint menu and a default model list.
Setup
- Open librechat.yaml (create it next to docker-compose if it does not exist).
- Add the endpoint block below and set RAPIDROUTER_API_KEY in .env.
- Restart. "Rapid Router" appears as an endpoint.
endpoints:
custom:
- name: "Rapid Router"
apiKey: "${RAPIDROUTER_API_KEY}"
baseURL: "https://rapidrouter.ai/api/v1"
models:
default: ["anthropic/claude-sonnet-5", "openai/gpt-5-mini", "google/gemini-3-flash"]
fetch: true
titleConvo: true
modelDisplayLabel: "Rapid Router"Field names as in LibreChat at the time of writing; their UI moves, the three values do not. LibreChat site.
Pick a model
The catalog lists every live model with its price per million tokens. For a coding tool, a strong model for edits and a cheap one for questions is the usual pair; the cost calculator shows what a month of your usage costs on each.
Common questions
Which model string do I put in LibreChat?
Any id from the catalog, in the vendor/model shape, for example anthropic/claude-sonnet-5. The models page lists every live id with its price; copy it exactly.
Does LibreChat need anything else to work with Rapid Router?
No. Rapid Router exposes the OpenAI chat completions API at https://rapidrouter.ai/api/v1, which is the shape LibreChat already sends. Streaming, tool calling and JSON mode work where the model supports them.
How is usage from LibreChat billed?
Per request at the provider's list price per million tokens, debited from your prepaid balance. Create a separate key for LibreChat and the dashboard shows its spend on its own; you can cap it monthly.
Is there a free allowance to test with?
Yes. Every account gets a daily allowance of free requests on eligible models before any top-up, so the first session costs nothing.