Continue Integration with The Grid | config.yaml Setup

Set up Continue with The Grid in config.yaml. Add your API key, point to the OpenAI-compatible endpoint, and map models to chat, edit, and autocomplete.

Continue is an open-source AI coding assistant for VS Code and JetBrains. The Grid plugs in as a standard OpenAI-compatible provider through config.yaml. Continue's role-based model assignment (chat, edit, apply, autocomplete, summarize, subagent) maps cleanly onto Grid instrument tiers.

Prerequisites

• Continue installed (VS Code extension or JetBrains plugin, latest version).

• A Grid account at app.thegrid.ai.

• Credits in your account. The Grid is prepaid; zero credits returns 402.

• A Grid consumption API key from Settings → API Keys → Create Consumption Key.

Setup

1. Store the key in Continue's local .env

Continue reads secrets from ~/.continue/.env (or the directory set by CONTINUE_GLOBAL_DIR). Add:

THEGRID_API_KEY=your-consumption-api-key-here

No quotes, no export, no spaces around =.

2. Add Grid instruments to config.yaml

Open ~/.continue/config.yaml. Continue creates this file the first time you open the side panel. Add Grid instruments under models:, each with the roles it's best suited for. Use instrument IDs from the current instruments list:

name: My Continue Config
version: 1.0.0
schema: v1

models:
  - name: Grid Code Prime
    provider: openai
    model: code-prime
    apiKey: ${{ secrets.THEGRID_API_KEY }}
    apiBase: https://api.thegrid.ai/v1
    roles:
      - chat
      - edit

  - name: Grid Code Standard
    provider: openai
    model: code-standard
    apiKey: ${{ secrets.THEGRID_API_KEY }}
    apiBase: https://api.thegrid.ai/v1
    roles:
      - apply
      - autocomplete

  - name: Grid Agent Prime
    provider: openai
    model: agent-prime
    apiKey: ${{ secrets.THEGRID_API_KEY }}
    apiBase: https://api.thegrid.ai/v1
    roles:
      - subagent

  - name: Grid Text Standard
    provider: openai
    model: text-standard
    apiKey: ${{ secrets.THEGRID_API_KEY }}
    apiBase: https://api.thegrid.ai/v1
    roles:
      - summarize

A few field-name details that catch people: provider: openai is Continue's generic OpenAI-compatible provider (there's no Grid-specific provider name). apiBase and apiKey are camelCase; base_url and api_key are silently ignored.

3. Add an embeddings provider

The Grid does not yet expose embedding instruments. Continue needs one for @codebase and @folder indexing. Pair The Grid with Voyage or a local Ollama embedding model:

  - name: Voyage Embeddings
    provider: voyage
    model: voyage-code-3
    apiKey: ${{ secrets.VOYAGE_API_KEY }}
    roles:
      - embed

Chat and edit work without this; only codebase indexing degrades.

4. Reload Continue

Continue watches config.yaml and reloads on save. If a change does not stick, run Developer: Reload Window from the command palette.

Verification

Open the Continue side panel, pick Grid Code Prime from the model dropdown, and try: "Refactor this function to use async/await instead of callbacks." Then test autocomplete by typing in a code file (code-standard should serve), and test inline edit with Cmd/Ctrl+I. If all three paths work, the integration is live.

Troubleshooting

401 or 402. 401 means you used a Grid trading key (or the env var didn't resolve). Generate a fresh consumption key and update ~/.continue/.env. 402 means your credits are at zero. Top up at app.thegrid.ai.

400 model not found. The model: field must be a valid Grid instrument ID. See the current instruments list. Typos like text_prime or code-pro fail.

Continue can't connect. Check provider: openai (not provider: thegrid), apiBase: https://api.thegrid.ai/v1 (camelCase, includes /v1), and that ~/.continue/.env has THEGRID_API_KEY=... with no quotes.

Some roles work, others fail silently. Every role you use must be in a model's roles: array. If chat works but apply fails, no model is mapped to apply. Add code-standard (or another instrument) under that role.

Embeddings or reranking on The Grid? Not yet. Pair The Grid with Voyage (voyage-code-3) or Ollama (nomic-embed-text) for the embed and rerank roles.