All systems operational
Live status and speed of the Umans Code gateway and its models, refreshed every 30 seconds. For each model we show its median time to first token and output speed.
… / 0production models operational
…gateway uptime · 90 days
0models in testing
…active issues
Gateway
API endpoint
API gateway Operational
api.code.umans.ai
…
service uptime · 24h
…
median TTFT · all models
Production
Models in production
TTFT = time to first token · tok/s = output tokens per second · p50 = median over the last 5 minutes. On each gauge the midpoint is that model's target; the marker sits further right when it's beating target (faster TTFT, higher throughput).
Model details are temporarily unavailable.
History
Gateway uptime
Changelog
Recent events & model lifecycle
Jun 242026
Retired: Umans GLM 5.1 Retired
umans-glm-5.1 was retired in favour of GLM 5.2. Requests to the old id now return a clear deprecation error pointing to umans-glm-5.2.
Jun 182026
Retired: Umans Kimi K2.6 Code Retired
umans-kimi-k2.6 was retired and superseded by K2.7. Requests to the old id now return a clear deprecation error pointing to umans-kimi-k2.7.
Jun 162026
Released to production: Umans GLM 5.2 Released
umans-glm-5.2 was released as the long-context model, with a 405K context window.
Jun 122026
Released to production: Umans Kimi K2.7 Code Released
umans-kimi-k2.7 was released as the recommended coding model (also served as umans-coder).
Past models 4 retired
Umans GLM 5.1 Retired
umans-glm-5.1 · GLM
Umans Kimi K2.6 Code Retired
umans-kimi-k2.6 · Moonshot
Umans Kimi K2.5 Retired
umans-kimi-k2.5 · Moonshot
Umans MiniMax M2.5 Retired
umans-minimax-m2.5 · MiniMax