DeepSeek V4.1 Flash hits 600+ tok/s on Isoquant, 8.7x faster than Claude Opus 5.5
ycombinator · x · 2026-11-06
Isoquant Labs says its AI-optimized deployment of DeepSeek V4.1 Flash 1017 runs at 600+ tokens/s — 8.7x faster than Claude Opus 5.5, shipping a playable Tetris in 10 seconds.
- Latency: 0.24s P50 / 1.16s P95 time to first token
- Pricing: $0.035 input / $0.005 cached / $0.37 output per 1M tokens
Drop-in compatible with existing OpenAI and Anthropic SDK integrations — just change the base URL. Live now, no waitlist.
More from Infra
- Hyperkernel generates SOTA megakernels across 11 domains, now on GitHub — MillionInt · 2026-11-06
- Musk: space will be the cheapest place to run superintelligence in 2-3 years — XFreeze · 2026-11-06
- Ex-Microsoft engineer: Azure runs 1M+ VM services, adds a datacenter every 4 days — viksit · 2026-11-06
- Mystery seller auctions $500M in data center loans, including Stargate financing — SumitGup · 2026-11-06
- Vercel launches Schedules public beta: agents can create cron jobs at runtime — cramforce · 2026-11-06
- Harbinger raises $240M Series D as electrification becomes an AI-era bottleneck — NYCounihan · 2026-11-06