The Best LLM on Every Prompt

Combine All Models to Create a Faster, Cheaper,
and Higher Performing Solution Than Any Single Model ->↓

Combine All Models to Create a Faster, Cheaper, and Higher Performing Solution Than Any Single Model ->↓

Read Docs Sign In

read docs try now

trusted by engineers at

It Starts with Your Query

api

All Models,
All Providers,
‍One API

All Models, All Providers, One API

Access all LLMs across all providers with a single API key and a standard API.

import requests
url = "https://api.unify.ai/v0/inference"
headers = {
"Authorization": "Bearer YOUR_UNIFY_KEY",
}

payload = {
"model": "mixtral-8x7b-instruct-v0.1",
"provider": "anyscale",
"arguments": {
"messages": [{
"role": "user",
"content": "YOUR_MESSAGE"
}],
"temperature": 50,
"max_tokens": 500,
"stream": True,
}
}

response = requests.post(
url, json=payload, headers=headers, stream=True
)

...

make your first request

import requests
url = "https://api.unify.ai/v0/inference"
headers = {
"Authorization": "Bearer YOUR_UNIFY_KEY",
}

payload = {
"model": "mixtral-8x7b-instruct-v0.1",
"provider": "anyscale",
"arguments": {
"messages": [{
"role": "user",
"content": "YOUR_MESSAGE"
}],
"temperature": 50,
"max_tokens": 500,
"stream": True,
}
}

response = requests.post(
url, json=payload, headers=headers, stream=True
)

...

make your first request

router

Get the Most
from Models with
Expert Routing

Get the Most from Models with Expert Routing

Automatically send your queries to the most appropriate model and get the best output, with the fastest providers, at the lowest cost.

performance

Constantly Achieve
‍Peak Performance

Systematically send your queries to the fastest provider, based on the very latest benchmark data for your region of the world, refreshed every 10 minutes.