Fraterna Logo Fraterna

Fraterna overview

How consorzi pool Venice API keys and route shared requests.

Fraterna lets a group combine Venice API keys into a shared pool. This gives developers, researchers, and friends more API capacity for projects they build together.

Fraterna is not a chat app or a replacement for Venice. It is an API proxy: your project sends requests to Fraterna, which routes them through an available Venice API key in your consorzio.

If you only use Venice for chatting, you probably do not need Fraterna, yet.

1. How Fraterna works

Members send requests using their own Venice API keys. Fraterna selects an available contributed key from the consorzio for each request.

Setup

  • - Sign in with your Venice API key.
  • - Create a consorzio, or join an existing one with an invite code.
  • - Point your OpenAI-compatible client at Fraterna.
  • - Invite Venice API users to add shared capacity.

Request routing

  • - Members send requests using their own Venice API keys.
  • - Fraterna selects an available Venice API key contributed by the consorzio for each request.
  • - Keys that are depleted, invalid, or temporarily limited are skipped when possible.
  • - Only members of a consorzio can use its shared inference budget.

Membership rules

  • - You can belong to only one active consorzio at a time.
  • - There is no member limit.
  • - You need a valid invite code to join.
  • - Members can leave at any time.
  • - If the owner leaves, ownership moves to the earliest remaining member.
  • - If the last member leaves, the consorzio is deleted.

2. API usage

After joining a consorzio, configure your app, script, or OpenAI-compatible client with Fraterna's base URL and your Venice API key.

Use https://fraterna.ai/api/v1 as the base URL in any OpenAI-compatible client. Your Venice API key must belong to an active consorzio to use its shared capacity.

For the complete request and response format, see the Venice API specification.

Base URL
Bearer token
your Venice API key
Vercel AI SDK TypeScript ยท venice-ai-sdk-provider
import { createVenice } from 'venice-ai-sdk-provider'
import { generateText } from 'ai'

const venice = createVenice({
    baseURL: 'https://fraterna.ai/api/v1',
    apiKey: 'your_venice_key',
})

const { text } = await generateText({
    model: venice('venice-uncensored-1-2'),
    prompt: 'Say hello in one sentence.',
})

console.log(text)
cURL 
curl -X POST https://fraterna.ai/api/v1/chat/completions \
  -H "Authorization: Bearer your_venice_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "venice-uncensored-1-2",
    "messages": [{"role": "user", "content": "Hello Fraterna"}],
    "stream": false
  }'
Node.js 
const response = await fetch('https://fraterna.ai/api/v1/chat/completions', {
    method: 'POST',
    headers: {
        Authorization: 'Bearer your_venice_key',
        'Content-Type': 'application/json',
    },
    body: JSON.stringify({
        model: 'venice-uncensored-1-2',
        messages: [{ role: 'user', content: 'What is Fraterna?' }],
    }),
})

const data = await response.json()

console.log(data.choices[0]?.message?.content)
Python 
import openai

client = openai.OpenAI(
    base_url="https://fraterna.ai/api/v1",
    api_key="your_venice_key"
)

response = client.chat.completions.create(
    model="venice-uncensored-1-2",
    messages=[{"role": "user", "content": "What is Fraterna?"}],
)

print(response.choices[0].message.content)
cURL Image generation
curl -X POST https://fraterna.ai/api/v1/image/generate \
  -H "Authorization: Bearer your_venice_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-image-turbo",
    "prompt": "A tiny watercolor painting of a smiling sun above a Venetian canal"
  }'

These examples include the key directly for clarity. In production code, store it in an environment variable and never commit it to version control.

Supported endpoints

  • POST/api/v1/chat/completionsText chat
  • POST/api/v1/image/generateNative Venice images
  • POST/api/v1/images/generationsOpenAI-compatible images
  • GET/api/v1/modelsAvailable models

3. Privacy and account access

Your Venice API key is used to sign in to Fraterna and authenticate API requests.

Fraterna does not provide account recovery. If you lose your Venice API key, you lose access to your Fraterna account.

Fraterna records successful requests using pseudonymous member IDs. Recorded technical details may include the endpoint, model, and API consumption.

4. Frequently asked questions

What is Fraterna?

Fraterna is an OpenAI-compatible API proxy for invite-only groups called consorzi. Members pool Venice API capacity, and Fraterna rotates requests across available contributed keys. It is for developers using the Venice API, not a chat app.

How does Fraterna pool Venice API keys?

Members contribute Venice API keys to a consorzio. For each request, Fraterna selects an available key and skips keys that are depleted, invalid, or temporarily rate-limited. Members keep ownership of their own keys.

Is Fraterna free to use?

Yes. Creating and joining a consorzio costs nothing. Inference capacity comes only from members' contributed Venice API keys.

Can I use Fraterna with OpenAI-compatible clients?

Yes. Point your client at https://fraterna.ai/api/v1 and use your Venice API key as the bearer token. Fraterna supports chat completions, image generation, and models endpoints.

What happens when the last member leaves?

If the last active member leaves, the consorzio and its membership records are permanently deleted. If the owner leaves while members remain, ownership transfers to the earliest remaining member.

Where can AI agents and LLMs find product details?

The LLM product overview summarizes the API and public pages.

Last updated: July 2026

Fraterna Fraterna