$UMBRA is live on pump.fun k6DhSa48q8itLQt33v6kHdjEzf5YJAHW1xdyi9Epump Buy on pump.fun →
Decentralized · Uncensored · Verified

AI that can't see you

Umbra routes your prompts through a network of independent GPUs — but the relay never reads them, no one stores them, and every worker is slashed for dishonest inference. Pay in USDC. Owned by no one.

network live · 0 workers · 0 tok/s
Contract k6DhSa48q8itLQt33v6kHdjEzf5YJAHW1xdyi9Epump
workers online
jobs served
network tok/s
audits passed
liars slashed
Why Umbra is different

Two things every other AI network gets wrong.

Centralized providers log your prompts and censor their models. The "decentralized" ones still pipe every prompt through one operator in plaintext, and have no way to tell if a worker actually ran the model. Umbra fixes both.

🔒

Sealed routing — the relay is blind

Your browser encrypts each prompt to the assigned worker's key using a NaCl sealed-box. The relay forwards ciphertext it physically cannot open, and the worker seals every token back to a one-time key only you hold. No operator sees your prompt. Nothing is stored. The competition admits their relay reads plaintext "to route it" — ours can't.

⚖️

Verifiable inference — liars get slashed

Every worker stakes $UMBRA and is continuously hit with canary challenges indistinguishable from real traffic. The relay recomputes the honest answer and compares. Run a cheaper model, fake your output, or cut corners and you fail the audit — your stake is slashed and you're ejected. Reputation, not just speed, decides who gets paid.

The flow

01

You seal

Your browser encrypts the prompt to the worker's public key.

02

Relay routes blind

It picks a worker by reputation × speed and forwards opaque bytes.

03

Worker answers

It decrypts, runs the model, and seals each token back to you.

04

You decrypt

Tokens stream into your tab. The relay saw nothing but ciphertext.

Models

Uncensored, all the way down.

Every model has had refusal behavior removed. Flat per-request pricing — you know the cost before you send. 1 credit = $0.01, bought with USDC.

Umbra Pro
8 credits · $0.08
  • Uncensored 8B
  • Runs in browser GPUs (WebGPU)
  • Fast, cheap, fully sealed
Umbra Max
12 credits · $0.12
  • Uncensored 27B
  • Tools + vision + large context
  • Native GPU workers
Umbra Max · think
16 credits · $0.16
  • Extended chain-of-thought
  • Hardest reasoning + agents
  • Plus umbra-code for the CLI
$UMBRA

The token captures the network's growth.

You don't need $UMBRA to use Umbra — inference is paid in USDC. $UMBRA is how the value flows back. Every job's margin and trading fees collect in a treasury that splits daily.

50% · buyback & burn
50% · staker rewards (USDC)

Stake $UMBRA to earn USDC, claim a daily free-credit allowance, and (if you run a worker) lift your cut from 70% to 80%. Workers stake against their own honesty — and lose it if they cheat.

Contract k6DhSa48q8itLQt33v6kHdjEzf5YJAHW1xdyi9Epump
REVENUE SPLIT PER JOB
70% worker
25% treasury
5% ref
WITH A STAKED WORKER BOOST
80% worker
15% tr
5%
treasury collected$0.00
burned to date$0.00
API

OpenAI-compatible. Built for agents.

Point any framework at Umbra by changing two things — base_url and api_key. Uncensored models, never logged, anonymous to the worker.

# pip install openai — then just repoint it
from openai import OpenAI

client = OpenAI(
    base_url="https://umbracompute.com/api/v1",
    api_key="sk-umbra-...",        # get one at umbracompute.com → settings → API
)
resp = client.chat.completions.create(
    model="umbra-max",             # uncensored 27B, sealed to the worker
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
# resp.umbra → { worker, worker_reputation, sealed: true }