GLM 5.3 Flash hits RunInfra day one: 254 tok/s, 1M context, $0.10/1M input
alejandroll10 · x · 2026-08-27
RunInfra has launched GLM 5.3 Flash (vendor-native FP8 from zai-org) on day zero, competing on speed, price and caching:
- 254.1 output tok/s, 703ms to first token, 1M-token context window
- Pricing: $0.10/1M input, $0.40/1M output, cached input at $0.01/1M with a reported 86–92% cache hit rate, making repeated prefixes nearly free
- OpenAI-compatible API — just change the base URL; tool calling, JSON mode and streaming supported
- Zero data retention: prompts are never stored or used for training
More from Infra
- MiniCPM-V 4.7 runs a 35B MoE multimodal model on phones with just 3GB memory — nevrekaraishwa2 · 2026-10-15
- Nvidia Is Now Worth More Than the Entire Indian Stock Market — theteknosaur · 2026-10-15
- NVIDIA joins EU's AI in Science Enablers, offering compute, training and cloud resources — nordicinst · 2026-10-15
- Open source's hardware trap: data centers crowd out consumer GPUs, local LLMs become a privilege — Dante_77A · 2026-10-15
- NVIDIA backs EU AI in Science push as 35 supercomputers to serve 3M researchers — NVIDIA Blog · 2026-10-15
- Jensen Huang: 2027 AI bottleneck is 35GW of power, revenue justifies the capex — BG2 Pod · 2026-10-15