Skip to main content
POST
Generate
Send a prompt to an eligible worker node and receive generated output plus usage metadata.

Request body

string
required
Input text for inference.
string
Model identifier (for example tinyllama).
integer
Maximum output tokens. Default is 256.
number
Sampling temperature between 0.0 and 2.0. Default is 0.7.

Example request

Success response

string
Unique job ID for this generation request.
string
Worker node that executed the inference.
string
Generated completion text.
object
Usage object with token and credits metadata.

Response example

Error responses

Last modified on February 21, 2026