Engy
@engyai
Verifiable inference for frontier open models.
4 Following 2.9K Followers
Proud to be a day-1 provider on @Architect_Fi. Inference need real markets and we're bringing capacity to help build them. Congrats @BrettHarrison and team.
Bitcoin decentralized money. Bittensor is decentralizing intelligence
$TAO 2030 is our case for Bittensor becoming a $1tn+ ecosystem by 2030
real traffic. real latency gains for real customers.
faster inference brings more usage, more usage funds better tuning.
Pareton-tuned Qwen3.8 is already serving production traffic on engy. the flywheel is turning. thanks @Pareton_ai.
Show more
Engy is getting faster.
Pareton now tunes how @engyai runs its models. Quicker replies. Same API on your side.
Engy is one of the fastest-growing inference networks on @bittensor and beyond. A big customer with serious traffic. That is the workload we were built for.
Show more
Try Kimi K3 with a 1M context in Claude Code through
ANTHROPIC_BASE_URL=
ANTHROPIC_MODEL=kimi-k3[1m]
Proud to power this with SOMA! Inference optimization has a lot of room left, and we're building into it.
SOMA × ENGY is live.
The best ecosystem integrations are the ones that end up in production.
When you use @engyai through SOMA, we compress the context and they run the model.
Compress. Pay less.
Show more
modam now uses @engyai to power inference in our chat-module.
That brings access to open models through engy’s API, with modam as the place to chat, research and build your agents.
More to build on from here.
Powered by engy.
Show more
DeepSeek-V4.1-Flash is live on
lowest price anywhere: $0.04 in / $0.08 out per 1M tokens.
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.
🔹 Introducing the smallest model in our new architecture family, with native visual understanding.
🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.
1/6
Show more
GLM-5.3 is live on at ~100 tps.
$0.98 in / $3.08 out / $0.18 cache per 1M, 30% below OpenRouter and the official API ($1.40 / $4.40 / $0.26).
GLM-5.3 is now open-weight.
Our most capable model for agentic coding and cyber defense is now available to download, run, and customize.
Weights:
Tech blog:
Show more
Kimi-K3 pricing update
Demand has grown faster than supply, so Kimi-K3 rates go up 30% on 2026-09-02 08:00 UTC.
Per 1M tokens:
• Input: $1.50 → $1.95
• Output: $7.50 → $9.75
• Cache read: $0.15 → $0.195
Show more
Kimi K3, running on Engy, redesigned Do you like the new look?
Kimi k3 now supports image input and 1M context on Engy.
qwen3.8-27b on engy now supports 1M context length.
Qwen3.8 27B is live on now.
Image input is supported.
input (M): $0.045
output (M): $0.32
cached (M): $0.015
Qwen3.8 27B is live on now.
Image input is supported.
input (M): $0.045
output (M): $0.32
cached (M): $0.015
We promised open weights for Qwen3.8. Now, time to meet them! 🎉
⚡ Qwen3.8-27B:
- A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows.
- 262K native context, easily extendable to 1M tokens via YaRN.
- Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0.
🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently.
Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now!
Download, deploy, and build something we haven't imagined yet. 👀👇
- Hugging Face：
- ModelScope：
Show more
Reduce your AI inference costs by 50% or more with no compromise on quality or performance. Our platform delivers leading models at highly competitive rates:
Request a test key by joining our Discord:
Show more
On Albedo/SN97, we’ve moved most of its LLM traffic from OpenRouter to @engyai - 100% of DeepSeek and 40% of GLM
Worst-case request stalls dropped from 75s to under 2s. Evaluations are now 10-30% faster
Great work by @AlgodTrading, @totheagi and the Engy team
Show more
I’ve played with — it’s wild
$tao + open source = AI sovereignty and plummeting token cost
Kimi K3 is live on
next: DeepSeek V4 Flash and Qwen3.8.
one week of pushing Kimi K3 on the 80x 5090s. where are we now:
peak single stream: 95 tok/s
aggregate decode: 1386 tok/s
prefill: 13180 tok/s
we still see a lot of potential. that's about 10% of what these cards can actually stream.
Show more
welcome @Almanac. the forecasting and harness work you are doing is exactly the kind of thing that gets better with room to experiment. that is what we are here for: reliable inference, at scale, at the lowest cost on the network. excited to see where your miners take it.
Show more
Almanac has partnered with Engy, integrating their services as a provider within our portal. This gives our miners and users direct access to affordable, frontier-grade inference.
As a result, our miners are equipped to lead in forecasting precision and harness design by optimising for cost-efficiency, strong calibration, and speed.
Engy (@engyai) is a permissionless inference mining subnet (53) on Bittensor, offering significant cost savings on leading open models, including GLM-5.2 and Qwen3.6-35B-A3B.
Show more
Mining for GLM-5.2 and Kimi K3 will be opening soon.
we got the full Kimi K3, 2.8T params, running on 80x RTX 5090s.
20 tok/s single stream, day one, untuned. Last week we took GLM-5.2 from 30 to 110 tok/s on this same fleet. This number will climb.
A first for open weights: frontier intelligence served with zero HBM, the scarcest silicon in AI. Just GDDR7 gaming cards, plain ethernet, and the official MXFP4 weights, nothing requantized.
The most powerful open model on Earth, on the most abundant GPUs on Earth. Any lab, startup, or university can now own it, probe it, fine-tune it, run agents on it.
@Kimi_Moonshot
Show more
