Skip to main content
POST
/
api
/
v3
/
inference
/
chat
/
completions
Generate Streaming Chat Completions
curl --request POST \
  --url https://api.nugen.in/api/v3/inference/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "nugen-flash-instruct",
  "messages": [
    {
      "role": "system",
      "content": "<string>",
      "name": "<string>"
    }
  ],
  "max_tokens": "2000",
  "prompt_truncate_len": 1500,
  "temperature": 1,
  "stream": false
}
'
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

​
Authorization
string
header
required

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

Headers

​
X-Session-ID
string | null

Body

application/json
​
model
string
required

The name of the model to use.

Example:

"nugen-flash-instruct"

​
messages
ChatCompletionRequestMessage · object[]
required

A list of messages comprising the conversation so far.

Minimum array length: 1
​
max_tokens
integer | null
default:2000

The maximum number of tokens to generate in the completion.

​
prompt_truncate_len
integer | null
default:1500

The size to which to truncate chat prompts.

​
temperature
number | null
default:1

What sampling temperature to use, between 0 and 2.

Required range: 0 <= x <= 2
​
stream
boolean | null
default:false

Whether to stream back partial progress as server-sent events.

Response

Streaming chat completion responses or complete response depending on stream parameter