Skip to main content
POST
/
v1
/
chat
/
completions
cURL
curl --request POST \
  --url https://api.ttapi.io/v1/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "model": "<string>",
  "stream": "false"
}
'
{
  "id": "chatcmpl-9ugiTupGJUmeRNqyqUvYO34GOUzyv",
  "object": "chat.completion",
  "created": 1723297597,
  "model": "gpt-3.5-turbo-0125",
  "choices": [
    {
      "index": 0,
      "message": {
        "content": "Hello! How can I help you?",
        "role": "assistant",
        "refusal": null
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 11,
    "completion_tokens": 17,
    "total_tokens": 28
  }
}
The TTAPI proxy for the Grok Chat Completions API uses the TTAPI platform key in the request header for authentication, while all other request and response parameters remain consistent with the official API. For details, refer to the Grok official documentation.

Authorizations

​
Authorization
string
header
required

You can obtain your API key from the TTAPI Dashboard.

Body

application/json
​
messages
object[]
required
Example:
[{ "role": "user", "content": "Hello!" }]
​
model
string
required

Model to use, see Supported Models

​
stream
boolean
default:false

Whether to use server-sent events for progressive response transmission

Response

Successful response

​
id
string
Example:

"chatcmpl-9ugiTupGJUmeRNqyqUvYO34GOUzyv"

​
object
string
Example:

"chat.completion"

​
created
integer
Example:

1723297597

​
model
string
Example:

"gpt-3.5-turbo-0125"

​
choices
object[]
​
usage
object
Last modified on March 16, 2026