Create a text completion
Send a single prompt string and receive a plain text completion, without the chat message structure.
/completionsSend a single prompt string and receive a plain text completion, without the chat message structure.
This is OpenAI's older completions contract, kept so that existing code
written against it keeps working. The completion object has no
reasoning_content field. Olive still reasons internally, but only
/chat/completions returns that
reasoning as a separate field. For anything new, prefer
/chat/completions.
Authorization
BearerAuth Your Avey API key, sent as Authorization: Bearer <key>. This is the header the OpenAI SDKs already send, so pass the key as the client's ordinary api_key and no further configuration is needed.
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
The body of a text completion request.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl https://api.avey.ai/llm/completions \ -H "Authorization: Bearer $AVEY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "olive", "prompt": "Summarize this discharge note in plain language:", "max_tokens": 512 }'{ "id": "cmpl-3b8d5c1a7e2f4d6b9c0a1e3f5d7b2a48", "object": "text_completion", "model": "olive", "choices": [ { "index": 0, "text": "You were treated for a chest infection and are going home on a five-day course of antibiotics.", "finish_reason": "stop" } ], "usage": { "prompt_tokens": 38, "completion_tokens": 274, "total_tokens": 312 }}