Bittensor-powered Engy hits 103B daily tokens, undercutting official API prices by up to 90%
markjeffrey · x · 2026-10-24
Engy, the inference gateway behind Bittensor Subnet 53, claims the cheapest inference on earth and published an exponential October growth curve: daily tokens grew from 5B to 74.4B, projected to top 103B today.
Its price list undercuts official APIs significantly:
- deepseek-v4.1-flash (1017, newly live): $0.30 input / $1.20 output per 1M tokens, cached input as low as $0.006 — about 90% below official
- qwen3.6-35b-a3b / qwen3.8-27b: outputs at $0.30 / $0.045 per 1M, roughly 10-13% of official pricing
- glm-5.3 / glm-5.2: outputs at $4.40 / $1.50, 30-59% discounts
- kimi-k3: $15.00 output, 35% off
- MiniMax-H3 image-to-video at $0.03/second
The platform markets zero data retention (ZDRT) and up to 1M context, with prices benchmarked against official API rates as of 2026-09-29 using a 3:1 input/output blend.
More from Infra
- Tencent's Hy-Nomas world model needs at least 24GB VRAM, dev complains — cocktailpeanut · 2026-10-24
- Humansand Speeds Up NVFP4 Decode Kernel by Up to 10% While Improving Accuracy — noahdgoodman · 2026-10-24
- Recursive's 40B Flint Hits ~200 tok/s on M3/M5 Ultra via MLX-VLM with Fused Metal Kernels — timshi_ai · 2026-10-24
- LiteLLM breach lesson: AI gateway logs are a secrets store — alvelda · 2026-10-24
- US electricity prices up 34% at investor-owned utilities since 2020 vs 19% public — randal_olson · 2026-10-24
- ExecuTorch now builds on Windows Snapdragon X Elite, demoing on-device Llama 3.2 1B — carrycooldude · 2026-10-24