Quickstart
Make a successful Qufas Chat Completions request in five minutes.
Quickstart
Complete these steps before sending your first request to Qufas AI's OpenAI SDK-compatible Chat Completions API.
- Create an account and sign in.
- Open Dashboard → Credits, add credits, and confirm that your balance is greater than
$0. Inference requires a positive prepaid balance; no free or promotional credit is assumed. - Open Dashboard → API Keys and create an API key. Copy the complete key when it is shown; later the dashboard displays only its prefix.
- Keep the key in server-side environment variables. Never expose it in browser code or commit it to source control.
Choose a current model
This quickstart currently uses kimi-k2.7-code. Use GET /v1/models for enabled official model IDs. Image examples are templates: replace <enabled-image-model-id> only after an image model is enabled. Qufas never silently remaps a model ID to another version. Confirm that it is enabled and review its current rate in Models & Pricing.
1curl https://qufas-ai.vercel.app/v1/models \2 -H "Authorization: Bearer $QUFAS_API_KEY"First request
Choose cURL, Python, or Node.js / TypeScript. Each tab setsQUFAS_API_KEY and calls the same Chat Completions endpoint.
Language
cURL
Best for a first terminal request and checking credentials.
How it works
Send a direct HTTP request without installing an SDK.
Set QUFAS_API_KEY, use https://qufas-ai.vercel.app/v1, and send requests to /chat/completions.
1export QUFAS_API_KEY="qf_sk_your_api_key"1curl https://qufas-ai.vercel.app/v1/chat/completions \2 -H "Authorization: Bearer $QUFAS_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "kimi-k2.7-code",6 "messages": [7 {8 "role": "user",9 "content": "Hello!"10 }11 ]12 }'Example response
1{2 "id": "chatcmpl_xxxxxxxxx",3 "object": "chat.completion",4 "created": 1750000000,5 "model": "kimi-k2.7-code",6 "choices": [7 {8 "index": 0,9 "message": {10 "role": "assistant",11 "content": "..."12 },13 "finish_reason": "stop"14 }15 ],16 "usage": {17 "prompt_tokens": 18,18 "completion_tokens": 26,19 "total_tokens": 4420 }21}First-request troubleshooting
| HTTP | Code | What to do |
|---|---|---|
| 401 | invalid_api_key | Check that QUFAS_API_KEY contains an active qf_sk_ key and that the Bearer header is present. |
| 402 | insufficient_balance | Open Dashboard, add credits, and confirm that the balance is greater than $0. |
| 404 | model_not_found | Call GET /v1/models again and use an ID returned for this API key. |
| 503 | model_unavailable | The model is not currently callable. Query GET /v1/models and choose an available ID; Qufas does not silently switch model versions. |
| 429 | rate_limit_exceeded | Honor Retry-After and retry with bounded exponential backoff. |
Save the x-qufas-request-id response header when asking for help. See Request IDs & Debugging and the Error Codes reference.
Was this page helpful?