DeepSeek reportedly running four V4 model versions, user says culling is coming to cut inference costs
teortaxesTex · x · 2026-09-09
User teortaxesTex argues DeepSeek consistently optimizes for minimal inference cost, which rewards running as few model types as possible. He lists four currently live versions — V4-Pro-0813, V4-Flash-0731, V4-Flash-Vision-Exp, and V4.1 — and predicts some will be culled. Pushing back on complaints, he notes DeepSeek isn't AWS: users have no long-term enterprise contracts and no guarantee their use case will be preserved. Unverified speculation: no official source for the version names or any deprecation plan.
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Running a local 9B as a coding agent: brief the big model to plan, let the small model execute — Electrical_Ninja3805 · 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