Inworld opens inference service; Flex tier can reject requests when busy at no charge
dr_cintas · x · 2026-10-15
Inference provider Inworld opened up its inference service, claiming it already processes tens of trillions of tokens a month with a stack built from the ground up for consumer AI apps.
The Flex tier has a distinctive design: as user cramforce found, it can simply turn requests down when busy — those cost nothing, but jobs must tolerate waiting, making it suitable only for deferrable workloads. For cost-sensitive, latency-tolerant inference tasks, it's a low-cost option worth considering.
More from Infra
- Mine Bittensor Subnet 92 by pointing Claude Code at one link — airesearch12 · 2026-10-15
- OpenAI infra lead leaves to start up after locking in double-digit GWs of compute — DesireeCachette · 2026-10-15
- Who Sells Data directory maps 159 AI training data vendors, compares Scale vs Mercor — cneuralnetwork · 2026-10-15
- Compute is the next commodity: building financial infrastructure for GPU markets — AnneliesGamble · 2026-10-15
- OCP slide reveals NVIDIA Rubin Ultra NVL576 will use CPO for scale-up networking — BenBajarin · 2026-10-15
- TensorFold ships macOS app for local LLM inference, reports 874 tok/s on RTX PRO 6000 — HankYeomans · 2026-10-15