U9 AI · DOCUMENTATION

Continue setup

Configure Continue with the correct U9 address, model and compatibility checks.

Compatibility and prerequisites#

This guide prepares Continue integration with U9 AI. You need an active U9 key, sufficient credit and an available model matching the endpoint. Official documentation was checked on 2026-10-24; this is not an end-to-end test of every client version or upstream model.

Setup steps#

1. Install Continue and merge the example models entry into your local config.yaml.
2. Use provider openai, the U9 apiBase and an actual model ID.
3. The apiKey value is a placeholder. Supply the real key through private local configuration and keep it out of version control.
4. This template starts with Chat Completions. Change useResponsesApi only after Responses compatibility is verified.

Configuration values#

name: U9 AI
version: 1.0.0
schema: v1
models:
  - name: U9 Chat
    provider: openai
    model: YOUR_CHAT_MODEL_ID
    apiBase: "https://u9ai.ai/v1"
    apiKey: YOUR_U9AI_API_KEY
    useResponsesApi: false
    roles:
      - chat

Important differences#

Only chat is enabled here. Agent, autocomplete and embeddings roles can require different models and endpoints.

Acceptance and handoff#

First follow quickstart to check GET /v1/models without generating content. Then test a short non-streaming request, streaming and any required tool-call round trip separately. Generation tests may incur charges. Record the request ID and verify cost analysis. For failures, include client version, model ID, endpoint, status and sanitized errors in a ticket. Do not blindly resubmit timed-out jobs.

Give this Markdown file to your developer or agent. Ask it to preserve current settings, substitute only available model IDs and report untested capabilities. Never put real keys in shared Markdown.

Official reference#

Continue