Documentation

Build on Gata

Gata is the full-stack AI network: an OpenAI-compatible model router, a coding agent, and autonomous 24/7 agents — all on one decentralized compute network. These docs cover all three.

Quickstart

The fastest way in is Gata Inference. It speaks the OpenAI API, so any OpenAI SDK works by changing two things: the base URL and your key.

1. Get an API key. Sign in to the console, open API keys, and create one. Copy it — it starts with sk-….

2. Point your client at Gata. Set the base URL to https://inference.apigata.net/v1 and use your key as a bearer token.

bash
curl https://inference.apigata.net/v1/chat/completions \
  -H "Authorization: Bearer $GATA_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "messages": [{ "role": "user", "content": "Hello, Gata!" }]
  }'

3. Or use the OpenAI SDK — same code, new base URL:

python
from openai import OpenAI

client = OpenAI(
    base_url="https://inference.apigata.net/v1",
    api_key="sk-...",  # your Gata key
)

resp = client.chat.completions.create(
    model="gpt-5",                       # or any of 40+ models
    messages=[{"role": "user", "content": "Route me to the best model."}],
)
print(resp.choices[0].message.content)

No rewrite required

Switch model providers by changing the model string — Gata handles routing, failover, and billing. Your existing OpenAI integration keeps working.

The Gata stack

Three products, one account and one wallet. Pick where to start:

Gata Inference

One OpenAI-compatible endpoint for 40+ models.

GataCode

A coding agent for your terminal and desktop.

GataAgent

A 24/7 personal agent that self-funds.

Get help

Questions or issues? Reach the team on Discord or Telegram. For account and billing, open the console.

Documentation — Gata