curl --request POST \
  --url http://your-model.soranova.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "meta-llama/Llama-3.3-70B-Instruct",
  "messages": [
    {
      "role": "user",
      "content": "What is the capital of France?"
    }
  ]
}'
{
  "id": "<string>",
  "choices": [
    {
      "message": {
        "role": "user",
        "content": "<string>"
      },
      "finish_reason": "stop"
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
string
required

The model to use for completion

​
messages
object[]
required
​
max_tokens
integer
default:2048

Maximum number of tokens to generate

​
temperature
number
default:0.6

Sampling temperature

​
stream
boolean
default:false

Whether to stream the response

Response

200 - application/json
Successful completion
​
id
string
required

Unique identifier for the completion

​
choices
object[]
required