Umans GLM 5.3 Flash Deprecated
deprecated · serving until Nov 1, 2026 · successor umans-deepseek-v4.1-flash
202.7tok/s
throughput · p50 · last 5 min
568ms
TTFT · p50 · last 5 min
100.00%
uptime · 24h
GLM-5.3-Flash is Z.ai's fast open-weights model for coding and agentic work: a 320B mixture-of-experts with 18B active parameters per token, the first natively multimodal release in the GLM-5 series with native image and video understanding, on a 1M-token context window. It always thinks at max effort by default; dial reasoning to low or high (thinking cannot be turned off). Billed per token ($0.15 / $0.50 / $0.03 per 1M; input / output / cache read). Deprecated: use `umans-deepseek-v4.1-flash` instead (sunset 2026-11-01).
Trends
Speed over the last 90 days
90 days agotoday
90 days agotoday
Changelog
Events for Umans GLM 5.3 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
Sep 92026
Released pay-per-token: Umans GLM 5.3 Flash Released
umans-glm-5.3-flash joins the lineup: GLM-5.3-Flash, the checkpoint that served here as the seat-gated pre-release lab since August 26: a 320B mixture-of-experts (18B active per token), the first natively multimodal release in the GLM-5 series with native image and video understanding, on a 1M context window. It always thinks at max effort by default; dial reasoning to low or high (thinking cannot be turned off). Billed per token: $0.15 / $0.50 / $0.03 per 1M (input / output / cache read). The pre-release window's metrics stay on the model's status page as its pre-release period (before Sep 9).