About 2 minutes · cURL request format verified in low-limit production checks
1. Sign in and check the model
Open the APIrove console. Check that your account can access the model, see its price and balance, and confirm its request format in the model directory. Read the pricing guide before you send a request.
2. Create a dedicated API key
In API key management, create a key for this application. Store it only on a trusted server in an environment variable or secret manager. Never paste it into browser code, a public repository, or a screenshot.
3. Send a small request
Replace both placeholders with your own key and an account-authorized model ID. This example uses the Responses endpoint:
export APIROVE_API_KEY='YOUR_API_KEY'
export APIROVE_MODEL='YOUR_ACCOUNT_MODEL_ID'
curl https://apirove.com/v1/responses \
-H "Authorization: Bearer $APIROVE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"'"$APIROVE_MODEL"'","input":"Say hello in one sentence.","max_output_tokens":16}'
Only use this endpoint if the selected model supports Responses. Some models use Chat Completions instead; follow the model details and API documentation.
4. Confirm the result
A successful response should contain the model output. Then open the signed-in usage page and confirm the request record and charge.
If the request fails
- 401: Check that the key is valid and sent as a Bearer token.
- 403: Check account status, model access, and endpoint compatibility.
- 429: Reduce request frequency and review account limits.
- 5xx: Check usage before retrying; a retry may create another request.
Next: read the API integration guide and verified model list.