Report Feedback

If you encounter a bug, a failed request you believe should have succeeded, or unexpected model behavior, here is how to get it in front of us quickly.

What to include#

A good bug report answers three questions: what did you send, what did you get back, and what did you expect?

Always include the X-Request-Id header from the failed response. This is a UUID-v7 trace ID that lets us pull the exact request, routing path, and upstream response from our logs in seconds. Without it, diagnosis is much slower.

# Capture the request ID from a cURL response
curl -i https://opendunes.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENDUNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "meta-llama/llama-4-maverick", "messages": [{ "role": "user", "content": "Hello" }] }' \
  | grep -i x-request-id

Include in your report:

• X-Request-Id value (from the response headers)
• HTTP status code returned
• The error and message fields from the response body (if present)
• The model slug you used
• A minimal reproduction of the request (no sensitive data — redact your key and any personal content)
• What you expected to happen

Where to reach us#

For billing disputes or credit discrepancies, always use the dashboard support channel — it has access to your account context.

Response time#

We aim to respond to bug reports within one business day (Algeria time, GMT+1). Production-blocking issues reported with a valid X-Request-Id are triaged faster.

Feature requests#

Feature requests and roadmap suggestions are welcome via GitHub Discussions or the dashboard feedback form. See What's live beyond chat for the current feature surface.