THE REAX NETWORK Live · netuid 92

AI by the people,
for the people.

REAX is Bittensor subnet 92: an open inference network for decision models. Anyone with a capable GPU can host the models, validators check every answer, and the network rewards correct, fast serving.

01 / HOSTING IS MINING

A decision model answers one focused question: route, escalate or choose what happens next.

Open models,
hosted by many.

Miners run pinned models; validators check answers and measure speed. Correct, fast miners earn more weight.

  1. 01 · SERVE

    Miners host the models

    Pinned models and runtimes make answers verifiable.

  2. 02 · VERIFY

    Validators check

    Fresh questions each round; wrong answers or model swaps score zero.

  3. 03 · REWARD

    Measurements earn weight

    Correct answers first, speed second.

  4. 04 · IMPROVE

    The network gets better

    Paused tracks follow published run-out rules.

PART 1 · INFERENCE · LIVE

Host the decision models

Pools: s1-fast/pro (NVIDIA), s1-lite (small GPUs, incl. Jetson Orin) and s1-cpu (CPUs).

PART 2 · COMPETITIONS · COMPETITION TRACKS PAUSED

Make it faster, make it smarter

Generalist paused since 30 Oct 16:30 UTC; REAX Engine after its 30 Oct slot. No next crowning is scheduled.

How mining works

03 / WHY DECISION MODELS

Millions of small decisions.
Most don't need a giant model.

Agents route requests, escalate cases and choose actions. Focused models provide fast, calibrated answers.

04 / GET STARTED

Use it. Mine it.
Check it.

USE

Call decision models

One Jev-compatible API. Euro billing; no on-chain payment.

Use the API

MINE

Serve on your GPU

Setup guide covers hardware, wallet, registration and node.

Start mining

VALIDATE

Run a validator

Recompute answers, measure speed, set weights. Public code.

Validator guide

REAX ENGINE

REAX Engine.
The code is public.

A prefill-only inference engine for decision models: one forward pass, no token generation. MIT License: the code is public and free for anyone to use, including companies. Mining and validating on subnet 92 are always free.

≈3.1×decisions per second vs. the reference server (Decision-Index-style traffic)
2.6×decisions per second on the JevBench public set
Samebenchmark scores, within noise

Measured with Perplexity Decider v1.1 27B in FP8 on one RTX PRO 6000 Blackwell GPU, against the model's reference server with the same harness.

Experimental shared-state mode: 6.0× (31.73 to 31.98 vs. 5.24 to 5.28 decisions per second) on Decision-Index-style traffic where requests carry several questions about one state; single-question requests stay at about 3.1×. No measurable change in the Decision Index. It is an approximation: 2.1 % of multi-question top-1 answers differ.

05 / REWARDS

Where miner
emissions go.

  • 30% Inference miners, shared by contribution (correct answers, then speed).
  • 20% REAX Engine competition: a faster engine for s1-fast; paused after its 30 Oct slot, with no next crowning scheduled.
  • 30% Generalist decision-model track, paused since 30 Oct 16:30 UTC; rank shares: 75%, 17%, 8%.
  • Not allocated to a track; unpaid portions are burned.

Inference is 30% from the first weight set at or after 2 Nov, 14:30 UTC (40% before; 50% before 30 Oct); allocation follows measured customer demand. REAX Engine remains 20%, generalist 30%; unpaid portions are burned. Both tracks are paused with no next crowning scheduled. The split can change; a change is announced at least 24 hours before it starts. See emission rules.

Rewards are variable and can be zero; hardware and registration are your costs. Nothing on this site is investment advice.

Scoring in detail   Competitions

06 / STATUS

Live on mainnet.
Netuid 92.

OPEN NETWORK · LIVE

Anyone can mine.

Since
14 Oct 2026, mainnet.
Registration
Open. Burn cost is set by chain; check before registering.
Pools
Four pools. One hotkey can serve several models (since block 9331987).
Validator
UID 3 (RTX PRO 6000, 96 GB); rounds about every 2 min.
Subnet 92 on taostats

EU TIER · BY CONTRACT

Contracted EU operators.

Who
EU companies processing data in the EU.
How
Business verification, operator contract and data-processing agreement.
Today
Requirements are written; admission is not open.
Send an operator inquiry

Live miner scores: miner leaderboard. Source: github.com/reaxlabs. More on the status page.

07 / ROADMAP

What comes
next.

  1. 01

    LIVE

    Inference mining

    Mainnet since 14 Oct. Capacity scoring v2 (15 Oct): pool pay follows verified throughput. Public miner board.

  2. 02

    PAUSED

    Competitions

    Paused: generalist since 30 Oct 16:30 UTC; REAX Engine after 30 Oct. No next crowning. REAX 1 base; Evaluation v3 when active.

  3. 03

    EMISSIONS

    Miner emission

    Miner emission splits between inference and competitions; see the mining page.

  4. 04

    LIVE

    Several GPUs behind one hotkey

    Live since 1.2.0rc8. Since 26 Oct 20:08 UTC: up to 2,560 decisions/s (s1-fast), 640/s (s1-pro) per hotkey. 1.2.0rc9.post5 added opt-in multinode. Since 21 Oct (block 9331987, 1.2.0rc10.post1), a hotkey can serve inference, hold one competition entry and serve 2–4 models.

  5. 05

    PLANNED

    Image-capable decision models

    Models that read images.

  6. 06

    PLANNED

    Mining on everyday hardware

    s1-lite (8 GB GPUs, Jetson Orin) and s1-cpu live; real-device calibration next.

  7. 07

    PLANNED

    EU operator admission

    Contracted EU operators for regulated traffic (GDPR, EU AI Act).

Questions? Read the FAQ. REAX is operated by productivity-boost.com, Germany.