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

Terminal
code --install-extension Continue.continue

2. 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.

config.yaml
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.

  1. Add MINIROUTER_KEY=mr-live-… to ~/.continue/.env.
  2. Set apiKey: ${{ secrets.MINIROUTER_KEY }} on each model.
config.yaml
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: 1000000

Copy 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.

Terminal
cn --config ./config.yaml -p "Generate a commit message for current changes"
-p
Runs headless, for scripts and CI.
--config
Uses another config file.

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.

Next steps

Esc