Umans GLM 5.2 Retired
no longer available; use umans-glm-5.3
retired Sep 10, 2026 · replaced by umans-glm-5.3 · weights ↗
85.4tok/s
throughput · p50 · whole period
1.79s
TTFT · p50 · whole period
98.85%
uptime · whole period
GLM 5.2 is our best model for coding right now, with a 400K context window for large codebases. Vision is available on the Anthropic Messages API (`/v1/messages`) only, through a server-side handoff (GLM 5.2 generates the text, Kimi preprocesses the image); that handoff will be retired soon in favour of more efficient client-side image handling. Deprecated: use `umans-glm-5.3` instead (sunset 2026-09-10).
Trends
Speed over its final 90 days
Jun 14, 2026retired Sep 10, 2026Sep 12, 2026
Jun 14, 2026retired Sep 10, 2026Sep 12, 2026
Changelog
Events for Umans GLM 5.2
Sep 102026
Retired: Umans GLM 5.2 Retired
umans-glm-5.2 reached its sunset and was retired in favour of GLM 5.3: it leaves the catalog and the model pickers, and its history stays on the past-models list. Requests still pinned to the old id keep routing for a short grace tail - migrate to umans-glm-5.3 (same GLM lineage, 1M context) now; a final cutoff date will be announced ahead of the hard stop.
Older events 1
Jun 212026
Released to production: Umans GLM 5.2 Released
umans-glm-5.2 was released as the long-context model, with a 405K context window, after a pre-release period that started Jun 16.