Skip to content
GlideflowAI Docs

Aider

Who it’s for

Section titled “Who it’s for”

Terminal-first developers who use Aider for repository edits and coding tasks.

Prerequisites

Section titled “Prerequisites”
  • Aider 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”
Terminal window
export OPENAI_API_BASE="https://api.glideflowai.com/v1"
export OPENAI_API_KEY="sk-your-key"
aider --model openai/glm-5.2

Test it

Section titled “Test it”

Launch Aider with the command above and ask it to explain one file. You can isolate API issues 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”
  • Missing openai/ before the model ID causes model resolution to fail.
  • Give reasoning models at least 512 output tokens when configuring limits.
  • HTTP 503 with 无可用渠道 means the model ID is wrong or unavailable for the key.