Providers wage price war over serving DeepSeek-v4-flash, user burns massive tokens for a few dollars
MaziyarPanahi · x · 2026-09-06
Developer Maziyar Panahi notes a price war among API providers over who can serve deepseek-v4-flash-0731 cheapest, saying he's never burned more tokens on an API for just a few dollars — a sign of how aggressive inference pricing has become.
More from Models
- Qwen-Drive-1.0-4B: Alibaba's compact 4B vision-language model for autonomous driving — solyarisoftware · 2026-09-06
- Shader eval puts Astra below GLM 5.3 flash on 3D spatial reasoning — teortaxesTex · 2026-09-06
- Claimed GPT-6 Astra + H3 Max combo builds an insanely fast realtime Blender renderer — jfischoff · 2026-09-06
- Users report ChatGPT has become 'handicapped' lately, forgetting context and demanding files — lonelyroom-eklaghor · 2026-09-06
- Early Astra hands-on: code quality and data analysis feel incremental, says developer — xeophon · 2026-09-06
- Annoyed by 'maximum length' prompts? Refreshing the page lets you keep chatting — hi-sci-collab · 2026-09-06