engy.ai Launches Chinese Open Models with Aggressive API Pricing
markjeffrey · x · 2026-08-08
Engy.ai, an inference platform on the decentralized Bittensor network, announced the launch of frontier open-source models like Kimi K3, DeepSeek V4 Flash, and GLM-5.2, focusing on low-cost inference for agents.
- Core Features: The platform emphasizes zero data retention (prompts and outputs are never stored or trained on) and is tuned for agentic traffic with high cache-hit rates.
- Pricing (per 1M Tokens):
- DeepSeek V4 Flash: Input $0.045, Output $0.09, Cached $0.009
- GLM-5.2: Input $0.68, Output $1.50, Cached $0.18
- Kimi K3: Input $1.50, Output $7.50, Cached $0.15
- Qwen3.6-35b-a3b: Input $0.045, Output $0.30, Cached $0.015
More from Infra
- Ex-OpenAI Co-founder Brockman Rumored to Tackle Silicon Supply Chain — beffjezos · 2026-08-08
- Running Cosmos3-Nano on RTX 5090: FP8/NVFP4 Quantization Fits in 32GB VRAM — fengwang_2_718281828 · 2026-08-08
- Fixing MiniMax H3 Black Frames on Legacy GPUs: FP16 Mix Cuts Inference 11x — Bubbly_Lawfulness_43 · 2026-08-08
- Microsoft Open-Sources BitNet: Running 100B LLMs on a Single CPU at 1.58 Bits — JafarNajafov · 2026-08-08
- Test: Running MiniMax H3 Video Generation on 12GB VRAM Stalls Over 5 Seconds — Silver-Spot-2763 · 2026-08-08
- Run a 70B Model Locally for Free: 5-Step Qwen 2.5 Guide with Dual 3090s — thisdudelikesAI · 2026-08-08