---
title: "Draft SillyTavern integration"
description: "Unverified draft settings for using SillyTavern with minirouter."
canonical_url: "https://minirouter.sh/integrations/sillytavern"
markdown_url: "https://minirouter.sh/integrations/sillytavern.md"
last_updated: "2026-08-04"
---

# SillyTavern + minirouter

Verification status: UNVERIFIED DRAFT
Confirm the current client fields and run the verification request before relying on this configuration.

Draft configuration for SillyTavern's Custom (OpenAI-compatible) source.

Base URL: https://api.minirouter.sh/v1
Get a key: https://minirouter.sh/key

## Settings

API Connections (the plug icon)

1. API: Chat Completion
2. Chat Completion Source: Custom (OpenAI-compatible)
3. 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.
4. Custom API Key: mr-live-… (your key)
5. Model ID: meta/llama-3.3-70b
   Press Connect first — the model list populates from our catalog.

## Draft configuration

Verify outside SillyTavern first — one request, literal values

```
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"}]}'
```

## Recommended models

Only use a model after confirming it appears in the live model catalog at https://minirouter.sh/api/v1/models.

- meta/llama-3.3-70b: General-purpose prose candidate.
- deepseek/deepseek-v3: Creative-writing candidate to evaluate.
- zai/glm-5: Long-context conversation candidate.
- mistral/ministral-14b: Smaller-model candidate for frequent retries.

## Troubleshooting

### Connect succeeds but the model list is empty

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.

### 404, HTML, or a parse error on every 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.

Error reference: https://minirouter.sh/docs/errors#invalid_request

### 401 on every request

Wrong or rotated key. Keys start with mr-live-; after a rotation the old key keeps working for 24 hours, then dies.

Error reference: https://minirouter.sh/docs/errors#invalid_api_key

### Response stops mid-sentence with a credits message

Balance hit $0 mid-stream. The stream ends with a terminal error naming the exact charge for tokens delivered — never a silent close.

Error reference: https://minirouter.sh/docs/errors#insufficient_credits