Fast, low-cost open decision models on one Jev-compatible API. Route, score & approve with probabilities. EU-hosted option. Powered by @reaxlabs (SN92).
@reaxlabs
Joined October 2026
- Tweets51
- Following52
- Followers500
- Likes27
You want to use Jev but they don't offer it GDPR compliant and hosted in EU 🇪🇺?
Consider REAX 1.3, our own model, which is #1 in the Hugging Face Decision Index 0.4.1. (Jev is #12)
We also offer mammoth-1 (as s1-pro-5), which leads the public-only ranking.
Available via our Jev-compatible API at decisionmodels.io
huggingface.co/spaces/multim…
REAX 1.3, our own model, is #1 on the Hugging Face Decision Index 0.4.1.
And mammoth-1, which we serve as s1-pro-5, leads the public-only ranking.
Both are live on our Jev-compatible API at decisionmodels.io
huggingface.co/spaces/multim…
REAX 1.3 is live on our API as reax-1.3:
EUR 0.40 per million input tokens, output tokens free.
Hosted in the EU, Jev-compatible interface.
decisionmodels.io/models/rea…
Introducing REAX 1.3
Our new open decision model, built with two models from our Bittensor miner competition and strong open models.
Results: our own run on public Hugging Face Decision Index items.
Available via API at decisionmodels.io
We now finally have the @DecisionModels X handle.
(formerly we had @decisiomodels_ with an underscore)
Need decision models without your data leaving the EU?
Our EU tier:
• EU requests always stay in the EU
• Priority on our EU capacity
• Never sent to the peer-to-peer network
• Prompts and answers not stored or used for training
• DPA included
decisionmodels.io/eu
Decision Models is now on New York Token Exchange and @TrustedRouter 🤝
nytokenexchange.com
decisionmodels.io
These are our own models, and we will of course serve them at decisionmodels.io.
We'll anounce more details soon.
Meet REAX 1, our open decision model built on Perplexity Decider v1.2.
Our own measurement: +2.4 points over its base, ahead in all 6 test draws and all 10 areas.
Open competition starts today 13:00 UTC:
=> Beat it, earn the rewards
see reax.co/competitions
Decision Models is now on @antseed 🎉
• Our decision models, including an EU tier
• Our Auto Router: it picks the best model for each request to give you excellent price/capability
Code and evals for Auto Router:
github.com/reaxlabs/auto-mod…
The engine inside of decisionmodels.io, and the reason why we most likely can serve these models faster than you may have seen them anywhere else.
Use leading Jev class models
- blazing fast and
- for crazy low prices
on decisionmodels.io/
We're releasing s1-llm-auto-router as open weights:
A small decision model that reads a request and picks the right LLM for it.
▸ 26 ms on a CPU, 22 languages, MIT license
▸ Our first use-case-specific decision model, from decisionmodels.io and Bittensor Subnet 92 (REAX)
▸ The best of the decision models we tested for this use case.
▸Now live on decisionmodels.io.
We're also announcing a joint project with msg group:
msg will evaluate the model in an internal project to make its use of LLMs more efficient. msg is one of Germany's top 5 IT consultancies (€1.5B revenue, 10,000+ employees).
Thank you, Dr. Ralf S. Engelschall (@engelschall), CTO of msg and one of the founding members of the Apache Software Foundation.
We believe use-case-specific decision models will become a huge market. More from us soon.
huggingface.co/decisionmodel…
How it compares on our own held-out routing test (2,175 synthetic requests in 22 languages, labels from a 5-LLM consensus, method in the model card):
It picks the same model as the gold label 74% of the time, the best of the decision models we tested, at 26 ms on a CPU.
On JevBench:
As its operator, we never rank our own models there. And a specialist like this isn't a fit for general decision-model benchmarks anyway, so we measured it on the task it was built for.
7
377
Hi, we're DecisionModels.
The best open decision models, served fast through one API:
→ s1-pro runs vLLM-SR d3, the most capable decision model in the world *
→ up to 4x faster on our own REAX engine
→ s1-fast from $0.019 per 1M input tokens (about 1.6x cheaper than Jev), output free
→ EU-hosted option with a DPA, built for GDPR and the EU AI Act
decisionmodels.io
* according to both the Decision Index on Hugging Face and the Capability Score on JevBench (our founder's own project)
Served by REAX, an open inference network on Bittensor subnet 92.
A gaming GPU is enough to participate.
reax.co
1
190