Anomaly undercuts Fireworks/Baseten by 60% on open model pricing
natolambert · x · 2026-11-22
Inference provider Anomaly says it is "popping the pricing bubble," hosting open models like DeepSeek Flash and GLM 5.3 at 60% below Fireworks/Baseten prices with higher throughput, all on its own GPUs. Nat Lambert notes price competition for open models is good but hard amid constrained GPU supply.
More from Infra
- Inkling 2 Mini on 2× RTX 3090: 557K context + vision at ~100 tok/s with NInfer-all — Sisuuu · 2026-11-22
- John Langford weighs in on FBT note: fixed-point convergence and quantized caching — JohnCLangford · 2026-11-22
- Fewer than 10 companies can safely move tenants across multi-tenant GPU clusters, argues compute-market skeptic — AccBalanced · 2026-11-22
- Tens of thousands of compute nodes power this multi-agent swarm architecture — hwchase17 · 2026-11-22
- Teknium shares Hermes telemetry: 92.4% of tokens are cache reads — Teknium · 2026-11-22
- Musk demos real-time AI video generation on half of one AI4 TRIP accelerator — jamesdouma · 2026-11-22