All services are online

Last updated on Aug 23, 2026 at 7:34am UTC

Model response times show the round-trip of a small synthetic request sent every 5 minutes from the US and EU — roughly time-to-first-token plus network overhead, not long-prompt latency.

Questions or seeing an issue we haven't posted yet? Join our Discord for live updates and support.

deepseek-v4-flash
99.161% uptime

Response times

gemma-4-31b
99.661% uptime

Response times

glm-5.2
99.881% uptime

Response times

glm-5.2-fast
99.725% uptime

Response times

glm-5.2-short
99.869% uptime

Response times

glm-5.2-short-fast
99.875% uptime

Response times

kimi-k2.7-code
99.658% uptime

Response times

kimi-k3
99.764% uptime

Response times

kimi-k3-fast
99.366% uptime

Response times

qwen3.5-397b
99.877% uptime

Response times

qwen3.5-397b-fast
99.882% uptime

Response times

qwen3.6-35b
99.917% uptime

Response times

qwen3.6-35b-fast
99.851% uptime

Response times

neuralwatt.com
100% uptime
30 days ago
Today
api.neuralwatt.com/health
99.936% uptime
30 days ago
Today
portal.neuralwatt.com
99.941% uptime
30 days ago
Today