Umans DeepSeek V4 Flash Retired
no longer available; use umans-deepseek-v4.1-flash
retired Nov 1, 2026 · replaced by umans-deepseek-v4.1-flash · weights ↗
333.8tok/s
throughput · p50 · whole period
1.17s
TTFT · p50 · whole period
100.00%
uptime · whole period
DeepSeek V4 Flash: DeepSeek's fast agentic coding MoE (284B total, 13B active), served from the official 0731 release on a 1M-token context. The cheapest production model in the lineup for real agentic work. Reasoning has four modes: non-think (none), think low (low, the default), think high (high) and think max (max). Served on our own GPU infrastructure with high availability. Deprecated: use `umans-deepseek-v4.1-flash` instead (sunset 2026-11-01).
Trends
Speed over its final 90 days
Aug 5, 2026retired Nov 1, 2026Oct 31, 2026
Aug 5, 2026retired Nov 1, 2026Oct 31, 2026
Changelog
Events for Umans DeepSeek V4 Flash
Nov 12026
Retired: Umans GLM 5.3 Flash, DeepSeek V4 Flash and Qwen3.6 35B A3B Retired
umans-glm-5.3-flash, umans-deepseek-v4-flash-0731 and umans-qwen3.6-35b-a3b reached their sunset and were retired in favour of DeepSeek V4.1 Flash: they leave the catalog and the model pickers, and their history stays on the past-models list. Requests still pinned to the old ids keep routing for a short grace tail; migrate to umans-deepseek-v4.1-flash now (1M context, native vision; umans-coder and umans-flash already run it). A final cutoff date will be announced ahead of the hard stop.
Older events 1
Aug 32026
Released pay-per-token: Umans DeepSeek V4 Flash Released
umans-deepseek-v4-flash-0731 joins the lineup as the cheapest way we serve real agentic work: $0.14 / $0.28 / $0.028 per 1M (input / output / cache read), a 1M context window, thinking at low effort by default (dial up high or max when a task deserves more). It is the new default for new chats and CLI setups. Founding users pay the 10x cheaper cache rate until Monday, August 10, 2026 (see /pricing). Served on our own GPU infrastructure with high availability.