GLM 5.3 Flash goes live on W&B serverless inference: 1M context, vision, $0.50/M output
wandb · x · 2026-09-09
A developer reports GLM 5.3 Flash is now live on W&B serverless inference, backed by CoreWeave, offering 1M token context, vision support, $0.50 per million output tokens, and fast speeds. The same author also spotted DeepSeek V4 live on the platform earlier. Third-party availability change for open-weight models; details unconfirmed by vendors.
Related event: Zhipu's GLM-5.3-Flash Lands on CoreWeave Serverless Inference(2 posts)→
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- SpaceX locks in $40B GPU financing deal with Apollo, the largest ever committed — TechCrunch AI · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27