Umans · Status · umans-deepseek-v4-flash-0731

← all models

Umans DeepSeek V4 Flash

umans-deepseek-v4-flash-0731 · DeepSeek-V4-Flash · DeepSeek

Operational

349.4tok/s

throughput · p50 · last 5 min

1.55s

TTFT · p50 · last 5 min

100.00%

uptime · 24h

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.

90 days agoin production since Aug 3, 2026today

Context

1049K

Max output

393K

Recommended

393K

Vision

Tools

Yes

Reasoning

Toggle · none/low/high/max

Weights

Full weights ↗

Trends

Speed over the last 90 days

daily medians · dashed line = target

throughput p50 · output tokens per second, higher is better

peak 317.7 tok/s · Aug 1now 317.4 tok/s

90 days agopre-release before Aug 3, 2026today

TTFT p50 · time to first token, lower is better

best 1.50s · Aug 1now 1.75s

90 days agopre-release before Aug 3, 2026today

Changelog

Events for Umans DeepSeek V4 Flash

incl. gateway-wide announcements

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.