← all models
Umans DeepSeek V4 Pro 0813 (lab) Playground Retired
umans-deepseek-v4-pro-0813-lab · DeepSeek
playground experiment; the V4 Pro 0813 pre-release window ran Aug 13 to 15, 2026; its metrics carry on the released model's status page as its pre-release period
retired Aug 15, 2026 · replaced by umans-deepseek-v4-pro-0813 · weights ↗
Retired
186.1tok/s
throughput · p50 · whole period
2.07s
TTFT · p50 · whole period
33.33%
uptime · whole period

DeepSeek V4 Pro as a Labs experiment, open for a short test window: temporary, not a permanent id. Served from DeepSeek's pre-release 0813 checkpoint: the flagship coding and reasoning MoE, ahead of its official release. Reasoning has three modes: non-think (none), think high (high, the default) and think max (max). Access is seat-gated through the Labs page while an experiment is live. It is offered at limited capacity and low availability, so expect it to be flaky and to go down under load: crash it, give it a moment, and try again. For production work we recommend umans-coder or umans-glm-5.2.

Aug 13, 2026retired Aug 15, 2026Aug 17, 2026
Trends

Speed over its final 90 days

daily medians · dashed line = target
throughput p50 · output tokens per second, higher is better
peak 189.7 tok/s · Aug 13final 186.1 tok/s
Aug 13, 2026retired Aug 15, 2026Aug 17, 2026
TTFT p50 · time to first token, lower is better
best 1.76s · Aug 13final 2.15s
Aug 13, 2026retired Aug 15, 2026Aug 17, 2026
Changelog

Events for Umans DeepSeek V4 Pro 0813 (lab)

incl. gateway-wide announcements
Aug 152026
Playground closed: Umans DeepSeek V4 Pro 0813 (pre-release) Testing
The V4 Pro 0813 pre-release window closed at the pay-per-token release: the production id now bills per token, so the seat-gated experiment on umans-deepseek-v4-pro-0813-lab ended rather than charge anyone by surprise. Thanks to everyone who pushed it, including through the August 14 outage, and shared findings; both the fixes and the metrics carried straight into the release. The model keeps serving as umans-deepseek-v4-pro-0813: the model stays.
Aug 132026
New Labs experiment: Umans DeepSeek V4 Pro 0813 Testing
A new lab opened on umans-deepseek-v4-pro-0813-lab: DeepSeek V4 Pro served from DeepSeek's own pre-release 0813 checkpoint - the flagship coding and reasoning MoE, ahead of its official release. Free and seat-gated while the experiment runs, served at limited capacity and low availability: it is a lab, so expect it to be flaky and to go down under load - crash it, give it a moment, and try again.