Skip to main content
POST
/
chat
/
completions
cURL
curl --request POST \
  --url https://api.comput3.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "hermes4:70b",
  "messages": [
    {
      "role": "system",
      "content": "<string>"
    }
  ],
  "max_tokens": 123,
  "temperature": 1
}
'
{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "system",
        "content": "<string>"
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}
Generate AI responses using Comput3’s language models.

​
Authentication Required

This endpoint requires a valid API key in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Example Request

curl
curl -X POST "https://api.comput3.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.1",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ],
    "max_tokens": 100,
    "temperature": 0.7
  }'

​
Request Body

  • model (string, required): The model ID to use (e.g., “hermes4:70b”, “hermes4:405b”, “deepseek-v3.1”, “kimi-k2”, “qwen3-coder:480b”, “qwen3-max”, “grok-code-fast-1”, “claude-sonnet-4”)
  • messages (array, required): Array of message objects with role and content
  • max_tokens (integer): Maximum number of tokens to generate
  • temperature (float): Sampling temperature (0.0 to 2.0)

​
Response

Returns the chat completion with the AI-generated response. 
{
  "id": "chatcmpl-123abc",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "deepseek-v3.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Authorizations

​
Authorization
string
header
required

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

Body

application/json

Chat completion request

​
model
enum<string>
required

The model to use for completion

Available options:
hermes4:70b,
hermes4:405b,
deepseek-v3.1,
kimi-k2,
qwen3-coder:480b,
qwen3-max,
grok-code-fast-1,
claude-sonnet-4
​
messages
object[]
required

The messages to complete

​
max_tokens
integer

Maximum number of tokens to generate

​
temperature
number

Sampling temperature

Required range: 0 <= x <= 2

Response

Chat completion response

​
id
string
​
object
string
​
created
integer
​
model
string
​
choices
object[]
​
usage
object