Continue: config.yaml for 666 AI

Continue reads models from config.yaml (the old config.json is deprecated). Use the openai provider with apiBase.

Replace YOUR-ENDPOINT with the endpoint shown on your API Key page after you sign up, and YOUR-KEY with your key. One key works for every model on 666 AI — Claude, GPT, Gemini, DeepSeek, Qwen and 200+ more.

config.yaml

# ~/.continue/config.yaml   (Windows: %USERPROFILE%\.continue\config.yaml)
name: My Config
version: 0.0.1
schema: v1
models:
  - name: Claude Sonnet 5.5 (666 AI)
    provider: openai
    model: anthropic/claude-sonnet-5.5
    apiBase: https://YOUR-ENDPOINT/v1
    apiKey: YOUR-KEY
    roles: [chat, edit, apply]
    capabilities: [tool_use]
  - name: Embeddings (666 AI)
    provider: openai
    model: openai/text-embedding-3-small
    apiBase: https://YOUR-ENDPOINT/v1
    apiKey: YOUR-KEY
    roles: [embed]

Notes

capabilities: [tool_use] is needed for Agent mode with custom model IDs.
Continue may call /responses for some OpenAI model names. On 666 AI, Claude models are served only by chat completions and /v1/messages — add useResponsesApi: false to be safe.

FAQ

Where is the file on Windows?

%USERPROFILE%\.continue\config.yaml — or open it from Continue's config dropdown (gear next to Local Config).

Create a free account All models Developer guides