Creates a raw text completion for the given prompt
Changed onGenerates a continuation of the prompt with no chat template applied — the prompt is passed to the model verbatim. Intended for clients that build the full prompt themselves, e.g. editor fill-in-the-middle (FIM) code autocompletion; include the model's FIM tokens in prompt directly. LLM models only.
post/v1/completions
Request
- The document declares no server URL.
- Authnone declared
Request body
Example request
{
"model": "qualcomm/Qwen3-4B-Instruct-2507",
"prompt": "def fibonacci(n):",
"max_tokens": 64,
"temperature": 0.2,
"stream": false
}Response
Successful response for non-streaming requests
Example response
{
"object": "text_completion"
}Changes
- info
added the optional property
usage/prompt_tokens_detailsto the response with the status
- info
- info
the request property
modelbecame optional
- info