Baidu serves DeepSeek V4 Flash at crazy fast speeds and low prices
NielsRogge · x · 2026-08-19
Users have observed that Baidu is serving the DeepSeek V4 Flash 0731 model at extremely fast speeds and very low prices. The model is a sparse mixture-of-experts with 13B active parameters out of 284B total, designed for coding, reasoning, and agent workflows. OpenRouter lists the price at $0.0786 per 1M input tokens with 1M context support.
More from Infra
- Phison CEO calls CXMT memory scare a 'ghost story', warns of materials shortage — BenBajarin · 2026-10-16
- Ben Bajarin: The Future of Compute Is Fungible as Hyperscalers Design for Workload Flexibility — BenBajarin · 2026-10-16
- AirLLM runs frontier-size models layer-by-layer: 671B on 12GB VRAM — Aiden_Tech_Ai · 2026-10-16
- NVIDIA Launches cuPotential in CUDA-X to Bring AI Agents to Semiconductor Materials Simulation — tomaszbednarz · 2026-10-16
- Q4-quantized coder model on 8-core CPU builds interactive solar system demo in one shot — IntrepidMindExplorer · 2026-10-16
- TokenSpeed MLA 2 ships for Vera Rubin: up to 3.44× faster Kimi K3 decode — zhyncs42 · 2026-10-16