The Best LLM on Every Prompt

Not Sure Which Model to Use?
Automatically Use The Best Model
for Your Task on Every Prompt ->↓

Not Sure Which Model to Use? Automatically Use The Best Model for Your Task on Every Prompt ->↓

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

Use our single API to query any model across all providers that support it.

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