Continue

Who it’s for

Developers who use Continue inside an IDE and want a custom OpenAI-compatible model endpoint.

Prerequisites

Continue installed
A GlideflowAI API key

Get your API key

Create a key in the GlideflowAI dashboard.

Base URL

Use https://api.glideflowai.com/v1.

Model ID

Start with glm-5.2. Copy the exact ID from the model catalog.

Minimal working config

Enter these values in Continue’s OpenAI-compatible provider fields:

Provider : OpenAI Compatible
Base URL : https://api.glideflowai.com/v1
API Key  : sk-your-key
Model ID : glm-5.2

Test it

Send a short prompt in Continue, or verify the endpoint directly:

curl https://api.glideflowai.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-5.2","messages":[{"role":"user","content":"Say OK"}],"max_tokens":512}'

Common errors

If the tool exposes an output-token limit, use at least 512 for reasoning models.
HTTP 503 with 无可用渠道 means the model ID is wrong or not enabled for the key.

Notes / limitations

Continue configuration formats can change between releases. This page documents provider values rather than a version-specific file schema.