Skip to main content
POST
/
generate
Generate
curl --request POST \
  --url https://api.example.com/generate \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "model": "<string>",
  "max_tokens": 123,
  "temperature": 123
}
'
{
  "id": "<string>",
  "node": "<string>",
  "output": "<string>",
  "usage": {}
}
Send a prompt to an eligible worker node and receive generated output plus usage metadata.

​
Request body

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

​
Example request

{
  "prompt": "Explain quantum tunneling in one paragraph.",
  "model": "tinyllama",
  "max_tokens": 256,
  "temperature": 0.7
}

​
Success response

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

​
Response example

{
  "id": "job_abc123",
  "node": "node-9006",
  "usage": {
    "tokens": 142,
    "credits_deducted": 1.42
  },
  "output": "Quantum tunneling occurs when..."
}

​
Error responses

StatusMeaningRetry
400Invalid request parameters.No
401Missing or invalid API key.No
402Insufficient credits.No
429Rate limited.Yes
503No healthy nodes available.Yes
Last modified on February 21, 2026