Integrations
SillyTavern
Chat with any MiniRouter model in SillyTavern.
SillyTavern is a self-hosted chat frontend for characters and roleplay. Its Custom (OpenAI-compatible) source runs on any chat model in the catalog, or the curated roleplay list, from one balance. See Roleplay for data handling and accountless keys.
Quick start
Step 1 of 5
Get your MiniRouter key
Open the key page in another tab. No account is required.
Key page
https://minirouter.sh/keyStep 2 of 5
Open API Connections
Return to SillyTavern and select the plug icon.
SillyTavern path
Plug icon → API Connections
Step 3 of 5
Choose the Custom source
Set these two menus before you paste the endpoint.
API
Chat Completion Source
Step 4 of 5
Paste the endpoint and your key
SillyTavern adds the request path, so the endpoint must stop at /v1.
Custom Endpoint (Base URL)
https://api.minirouter.sh/v1Do not add /chat/completions.
Custom API Key
Your mr-live-… keyGet keyStep 5 of 5
Connect and send a test
Press Connect. Choose the starter model from the list, then use Test Message.
Starter model
zai/glm-5.3-flash1 / 5
Switch models
Connect loads the catalog into Model ID. You can also type any ID, even one missing from the list.
Save connection profiles
A profile stores the API type, server URL, key and model. Save one per model, then switch with a slash command.
- /
profile-create GLM - Saves the current connection as GLM.
- /
profile GLM - Switches to it.
- /
profile-list - Lists your profiles.
Size each turn
These settings shape every turn:
- Context (tokens)
- Most SillyTavern sends as the prompt. Lower it to cut input cost.
- Response (tokens)
- Most the model writes back.
- Streaming
- Shows the reply as it arrives. See Streaming.
Keep Context below the window on the model's page in Models. A prompt over the window fails with context_too_long.
Keep spend in check
Every swipe and regenerate is a new, billed request.
Recommended modelsBrowse every model in the catalog.
zai/glm-5.3-flash- Best current intelligence/input-cost balance with a 1M-token window.
openai/gpt-5.6-luna- High-intelligence alternative with a 1.05M-token window.
deepseek/deepseek-v4-flash-0731- Lowest input rate on this list for repeatedly sent chat history.
google/gemini-3.8-flash- Higher-cost multimodal alternative with a 1M-token window.
Troubleshooting
Connect succeeds but the model list is empty
Check that the endpoint is exactly https://api.minirouter.sh/v1. 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: 400 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: 401 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: 402 insufficient_credits.
Every error code, with its fix: Errors.