All guides / Coding assistants

Use XHuoAPI in Continue

Continue is configured from a single YAML file. Any OpenAI-compatible endpoint uses provider: openai plus an apiBase field.

Before you start

Verify first

Before touching the tool, confirm the key and model work with curl. This rules out half of the 'I configured it and nothing happens' cases.

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v3.2","messages":[{"role":"user","content":"ping"}]}'

Steps

1

Open the config file: ~/.continue/config.yaml on macOS/Linux, %USERPROFILE%\.continue\config.yaml on Windows. Create it if missing.

2

Add model entries under models. The same apiKey and apiBase can be reused for several models; roles decide whether a model is used for chat, edit or apply.

name: XHuoAPI
version: 0.0.1
schema: v1

models:
  - name: DeepSeek V4 Pro
    provider: openai
    model: deepseek-v4-pro
    apiBase: https://api.xhuoapi.ai/v1
    apiKey: sk-...
    roles: [chat, edit, apply]
    capabilities: [tool_use]

  - name: Claude Sonnet 5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.xhuoapi.ai/v1
    apiKey: sk-...
    roles: [chat]
    capabilities: [tool_use, image_input]
3

Continue reloads automatically on save. If a config.json also exists, config.yaml takes precedence.

Notes

Continue only enables tool calling for a model if capabilities lists tool_use; same for image_input. Without them the model is treated as text-only.
Stop the base URL at /v1. Do not append /chat/completions; the client adds that path itself and you will get a 404 if you include it.

Commonly used models

These are common choices for this kind of tool; click a model to see its price in each tier. The full list is on the pricing page.

Steps follow the tool's current official documentation; the UI may change after updates. Tell us if something no longer matches.