Skip to content
GlideflowAI Docs

OpenCode

Who it’s for

Section titled “Who it’s for”

Terminal users who want OpenCode to call a custom OpenAI-compatible endpoint.

Prerequisites

Section titled “Prerequisites”
  • OpenCode installed
  • A GlideflowAI API key

Get your API key

Section titled “Get your API key”

Create a key in the GlideflowAI dashboard.

Base URL

Section titled “Base URL”

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

Model ID

Section titled “Model ID”

Start with glm-5.2. Copy exact IDs from /models.

Minimal working config

Section titled “Minimal working config”

Use these values in a custom OpenAI-compatible provider:

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

Test it

Section titled “Test it”

After saving the provider, ask OpenCode to answer with OK. Test the endpoint separately with:

Terminal window
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

Section titled “Common errors”
  • Reasoning models need at least 512 output tokens for a useful first response.
  • HTTP 503 with 无可用渠道 means the model ID is wrong or unavailable for the key.

Notes / limitations

Section titled “Notes / limitations”

OpenCode configuration filenames and schemas can vary between versions.