Integrations
Continue
Run Continue's chat, edit and agent on any model in the MiniRouter catalog.
Continue is an open-source coding agent for VS Code, JetBrains and the terminal. Add MiniRouter models to its config.yaml through the openai provider to use any model in the catalog, or a router, with one balance and per-key spend limits.
1. Install Continue
code --install-extension Continue.continueSettings → Plugins → Marketplace, search Continue, then Install.
npm i -g @continuedev/cli2. Create a key
Create a key for Continue.
3. Add the models
Open ~/.continue/config.yaml (or the gear icon → Configure) and add the entries under models. Replace the key.
models:
- name: GLM 5.3 Flash (minirouter)
provider: openai
model: zai/glm-5.3-flash
apiBase: https://api.minirouter.sh/v1
apiKey: mr-live-YOUR-KEY-HERE
roles: [chat, edit, apply]
- name: GPT 5.6 Sol (minirouter)
provider: openai
model: openai/gpt-5.6-sol
apiBase: https://api.minirouter.sh/v1
apiKey: mr-live-YOUR-KEY-HERE
roles: [chat, edit, apply]4. Send a prompt
Pick a MiniRouter model from Continue's model dropdown, send one prompt, then open Activity. The request lists its model, tokens and exact cost.
Keep the key out of config
Continue reads secrets from ~/.continue/.env, so config.yaml can be shared.
- Add
MINIROUTER_KEY=mr-live-…to~/.continue/.env. - Set
apiKey: ${{ secrets.MINIROUTER_KEY }}on each model.
models:
- name: GLM 5.3 Flash (minirouter)
provider: openai
model: zai/glm-5.3-flash
apiBase: https://api.minirouter.sh/v1
apiKey: ${{ secrets.MINIROUTER_KEY }}
roles: [chat, edit, apply]
defaultCompletionOptions:
contextLength: 1000000Copy contextLength from the model's page in Models.
Roles
roles decides where Continue offers each model. A cheaper model can take edit and apply.
- chat
- Chat and Agent mode.
- edit
- Rewriting a selection in place.
- apply
- Applying a suggested change to the file.
Routers and presets
Add each as its own model entry, then pick it from the model dropdown.
- minirouter/
auto: code - Picks a model with reliable tool calling. See Auto router.
- minirouter/
auto: cheap - Cheapest model that still answers well.
- @preset/
your-slug - Your saved models and instructions. See Presets.
A preset lets you change the model from the dashboard without editing config.yaml.
Run headless
cn -p runs one prompt without the TUI. It reads ~/.continue/config.yaml unless you pass --config.
cn --config ./config.yaml -p "Generate a commit message for current changes"- -p
- Runs headless, for scripts and CI.
- --config
- Uses another config file.
Recommended modelsBrowse every model in the catalog.
zai/glm-5.3-flash- Best current balance of coding ability, agentic performance, context and cost.
openai/gpt-5.6-sol- Higher-intelligence option when task quality matters more than spend.
spacexai/grok-4.6- Strong agentic alternative with a 500K-token window.
google/gemini-3.8-flash- Multimodal coding 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.
402 before any tokens arrive
Balance below the estimated cost of the request. Top up (from $0.50 with direct Solana payments) — and watch the x-minirouter-balance-usd header, the low-balance signal every response carries.
Error: 402 insufficient_credits.
Autocomplete is slow or absent
If your installed version supports a separate autocomplete role, choose a suitable model from the current live catalog.
Every error code, with its fix: Errors.