POST
/
v1
/
chat
/
completions
{
  "choices": [
    {
      "finish_reason": "<string>",
      "index": 123,
      "message": {
        "content": "<string>",
        "function_call": {
          "arguments": "<string>",
          "name": "<string>"
        },
        "role": "<string>"
      }
    }
  ],
  "created": 123,
  "id": "<string>",
  "model": "<string>",
  "object": "<string>",
  "usage": {
    "completion_tokens": 123,
    "prompt_tokens": 123,
    "total_tokens": 123
  }
}

Body

application/json
frequency_penalty
number | null
function_call
functions
object[] | null
ignore_eos
boolean | null
logit_bias
object | null
max_tokens
number | null
messages
object[]
required
model
string
required
n
integer | null
octoai
object | null

OctoAI specific extensions for a chat completion request.

presence_penalty
number | null
repetition_penalty
number | null
response_format
object | null
stop
stream
boolean | null
temperature
number | null
top_p
number | null
user
string | null

Response

200 - application/json
choices
object[]
required
created
integer
required
id
string
required
model
string
required
object
string
default: chat.completion
usage
object
required

An OpenAI API compatible schema for a chat completion stats.

Was this page helpful?

List hardware instance typesCreate Completion