Continue

Continue runs in VS Code and JetBrains and is configured from a YAML file. Inferray goes in as the openai provider with a custom apiBase.

Add the model

Open ~/.continue/config.yaml and add an entry under models:

name: My Config
version: 0.0.1
schema: v1

models:
  - name: Claude Opus 4.8
    provider: openai
    model: claude-opus-4-8
    apiBase: https://api.inferray.com/v1
    apiKey: inferray_...

provider: openai selects the wire format, not the vendor — it is what routes the request through the OpenAI-compatible path at your apiBase. model is the Inferray model id, so Claude and Gemini ids belong there too.

Add more models

Each entry in the list becomes a separate option in Continue's model dropdown, so add one block per model you want to switch between:

models:
  - name: Claude Opus 4.8
    provider: openai
    model: claude-opus-4-8
    apiBase: https://api.inferray.com/v1
    apiKey: inferray_...
  - name: GPT-5.5
    provider: openai
    model: gpt-5.5
    apiBase: https://api.inferray.com/v1
    apiKey: inferray_...

Every id in the catalogue can be used this way. Continue reads its models from this file rather than discovering them, so each one you want needs its own block.

The config file holds your key

config.yaml takes the key as a literal string, so treat the file as a secret: keep it in your home directory rather than the repo, and if you do commit a project-level config, put a placeholder in it and keep the real key in the home-directory file.