RunInfra Launches DeepSeek V4 Pro: 1M Context, 207 tok/s, Low Cost
alejandroll10 · x · 2026-08-19
RunInfra has launched DeepSeek V4 Pro, featuring full precision, 1M token context window, and speeds of 207 tok/s. Pricing is set at $0.60/1M input tokens and $1.90/1M output tokens. With 95% cache hit rate, the effective input cost drops to approximately $0.06/1M. The post contrasts this with DeepSeek's recent move to peak pricing, positioning RunInfra as a stable and cheaper alternative.
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