Integrations
Agnai
Chat with any MiniRouter model in Agnai.
Agnai is a multi-user character chat app, hosted at agnai.chat or on your own machine. Its Third-Party preset runs on any chat model in the catalog, or the curated roleplay list, from one balance. See Roleplay for data handling and accountless keys.
1. Open Agnai
Open agnai.chat.
npm install agnai -g
agnaiThen open http://localhost:3001.
2. Create a key
Create a key. Optionally test it before opening Agnai.
export MINIROUTER_KEY=mr-live-YOUR-KEY-HERE
curl https://api.minirouter.sh/v1/chat/completions \
-H "Authorization: Bearer $MINIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"zai/glm-5.3-flash","messages":[{"role":"user","content":"ping"}]}'3. Create the preset
Open Settings → AI Settings → Third-Party preset and fill in:
- AI Service
- Third-Party
- Third Party Format
- OpenAI Compat (Chat)
- Third Party URL
https://api.minirouter.sh/v1Never append /chat/completions — Agnai adds the path itself.- Third Party Key/
Password mr-live-… (your key)- OpenAI Model Override
zai/glm-5.3-flash
4. Send a message
Choose the preset from the chat menu's Preset and send a message. Open Activity to see its model, tokens and exact cost.
Switch models
Open the model picker, type into Manual Model ID, then Confirm. Any model ID works.
Two kinds of preset
- Agnai preset
- Service, URL, key, model and samplers. Pick one per chat from the chat menu's Preset.
- MiniRouter preset
- Models and fallbacks on our side. Create one in Presets, then send
@preset/your-slugas the model.
Size each turn
- Context Size
- Most Agnai sends as the prompt. Lower it to cut input cost.
- Response Length
- Most the model writes back.
- Stream Response
- Shows the reply as it arrives. See Streaming.
Keep Context Size 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 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
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.
Works self-hosted, fails on the hosted instance
The hosted app makes the request from its own servers unless Use Local Requests is enabled. Nothing on our side distinguishes the two — check the preset is actually selected for the character you are chatting with, since Agnai stores a preset per character.
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.