SillyTavern + minirouter
Draft configuration for SillyTavern's Custom (OpenAI-compatible) source.
Settings
API Connections (the plug icon)
In order
- APIChat Completion
- Chat Completion SourceCustom (OpenAI-compatible)
- Custom Endpoint (Base URL)https://api.minirouter.sh/v1
If models fail to load, try adding /v1. Do NOT add a /chat/completions suffix — SillyTavern appends that path itself.
- Custom API Keymr-live-… (your key)
- Model IDmeta/llama-3.3-70b
Press Connect first — the model list populates from our catalog.
curl https://api.minirouter.sh/v1/chat/completions \
-H "Authorization: Bearer $MINIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"meta/llama-3.3-70b","messages":[{"role":"user","content":"ping"}]}'Draft candidates · 4 models
All models →Only rows confirmed in the current live catalog are linked. A plain row is a draft recommendation, not a claim that the model is currently available. Paste ids exactly as written, author/name.
When it fails
- SymptomConnect succeeds but the model list is emptyCodeclient-side
Check the endpoint reads exactly https://api.minirouter.sh/v1 — try adding /v1 if you pasted the bare host into an older build, and remove any /chat/completions suffix.
- Symptom404, HTML, or a parse error on every requestCodeinvalid_request
Almost always the base URL. Use https://api.minirouter.sh/v1 — the bare host without /v1 also works, but never append /chat/completions to the base URL field; the client adds that path itself. docs/errors#invalid_request →
- Symptom401 on every requestCodeinvalid_api_key
Wrong or rotated key. Keys start with mr-live-; after a rotation the old key keeps working for 24 hours, then dies. docs/errors#invalid_api_key →
- SymptomResponse stops mid-sentence with a credits messageCodeinsufficient_credits
Balance hit $0 mid-stream. The stream ends with a terminal error naming the exact charge for tokens delivered — never a silent close. docs/errors#insufficient_credits →
Every API error string carries a URL resolving to /docs/errors.
Other roleplay frontends
Why this workload bills the way it does, what it costs to contain, and which models suit it: /use/roleplay.