Prepare three settings
| Setting | Value | Purpose |
|---|---|---|
| Base URL | https://vectide.cn/v1 | For SDKs and clients supporting a custom endpoint |
| API Key | VECTIDE_API_KEY | Create it in the dashboard; store it in an environment variable or credential store |
| Model ID | glm-5.3 | This example uses GLM-5.3; the account must have access |
These are examples for you to run with your own credentials and allowance. Keep keys out of public repositories, browser frontend code and screenshots.
macOS / Linux: curl example
Set VECTIDE_API_KEY in the current terminal. This example starts without streaming so the status and response body are easier to inspect.
curl https://vectide.cn/v1/chat/completions \
-H "Authorization: Bearer $VECTIDE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5.3","messages":[{"role":"user","content":"Reply with a short greeting."}],"stream":false}'Windows PowerShell
After setting the environment variable in your current session, send the request below. Choose an exact model ID your account can access.
$body = @{
model = "glm-5.3"
messages = @(@{ role = "user"; content = "Reply with a short greeting." })
stream = $false
} | ConvertTo-Json -Depth 5
Invoke-RestMethod -Method Post `
-Uri "https://vectide.cn/v1/chat/completions" `
-Headers @{ Authorization = "Bearer $env:VECTIDE_API_KEY" } `
-ContentType "application/json; charset=utf-8" `
-Body ([System.Text.Encoding]::UTF8.GetBytes($body))Check that the request completed
Look for message content in choices and reconcile the request in the dashboard. HTTP 200 alone does not prove that a streamed response completed; inspect termination, error events and disconnects when enabling streaming.