POST/v1/chat/completions

Chat Completions

Create chat completions using state-of-the-art language models. This endpoint is compatible with the OpenAI API format.

Request

Example Request

curl https://api.assisters.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "assisters-chat-v1",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Parameters

modelrequiredstring

ID of the model to use. See the models catalog for available options.

Available models:

assisters-chat-v1 - Fast and efficient
assisters-chat-v2 - High performance
assisters-vision-v1 - Multimodal support

messagesrequiredarray

Array of message objects representing the conversation history.

Message object:

role (string) - One of: system, user, assistant
content (string) - The message content

temperatureoptionalnumberdefault: 0.7

Sampling temperature between 0 and 2. Higher values make output more random, lower values make it more focused and deterministic.

max_tokensoptionalintegerdefault: 1024

Maximum number of tokens to generate in the completion.

top_poptionalnumberdefault: 1

Nucleus sampling parameter. Consider tokens with top_p probability mass.

streamoptionalbooleandefault: false

If set to true, partial message deltas will be sent as server-sent events. Currently not supported.

Response

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "assisters-chat-v1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 9,
    "total_tokens": 29
  }
}

Response Fields

id - Unique identifier for the completion
object - Object type, always "chat.completion"
created - Unix timestamp of creation time
model - Model used for completion
choices - Array of completion choices
usage - Token usage statistics

Error Codes

Code	Description
`401`	Invalid or missing API key
`400`	Invalid request body or parameters
`403`	API key doesn't have access to this model
`429`	Rate limit exceeded or insufficient quota
`500`	Server error

Code Examples

Python

example.py

from assisters import Assisters

client = Assisters(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="assisters-chat-v1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing"}
    ],
    temperature=0.7,
    max_tokens=1024
)

print(response.choices[0].message.content)

Node.js

example.js

import Assisters from 'assisters';

const client = new Assisters({
  apiKey: process.env.ASSISTERS_API_KEY
});

const response = await client.chat.completions.create({
  model: 'assisters-chat-v1',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain quantum computing' }
  ],
  temperature: 0.7,
  max_tokens: 1024
});

console.log(response.choices[0].message.content);