Text Generation

CompactifAI API offers powerful text generation capabilities through our completion endpoints. Our compressed models can generate coherent, contextually relevant text for a wide range of applications while offering significant cost and performance advantages over uncompressed alternatives.

Basic Usage

import requests

API_URL = "https://api.compactif.ai/v1/completions"
API_KEY = "your_api_key_here"

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

data = {
    "model": "cai-llama-4-scout-slim",
    "prompt": "Write a short story about a robot that learns to paint:",
    "max_tokens": 250,
    "temperature": 0.7
}

response = requests.post(API_URL, headers=headers, json=data)
print(response.json()["choices"][0]["text"])

Parameters

Parameter	Type	Description
model	string	ID of the compressed model to use
prompt	string	The prompt to generate completions for
max_tokens	integer	Maximum number of tokens to generate
temperature	number	Controls randomness (0-2)
top_p	number	Controls diversity via nucleus sampling
n	integer	Number of completions to generate
stop	string or array	Sequences where the API will stop generating

Please refer to our API Reference or the OpenAI API reference for more information on the parameters.