FreebuffLatency

Status

All systems operational
freebuff.com and Freebuff Cloud
Serving this page.
Operational
Freebuff API (CLI and Desktop)
Accepting requests.
Operational
Models
7 of 10 served in the last 3 hours.
Operational

Models

GLM 5.3 FlashIdle
DeepSeek V4.1 Flash 10/171.6s median to first token (24h)
DeepSeek V4.1 Flash Fast 10/171.7s median to first token (24h)
Muse Spark 1.33.0s median to first token (24h)
Solar Mini 43.0s median to first token (24h)
Solar Pro 43.5s median to first token (24h)
GPT-6.1 SolIdle
GPT-6.1 Terra4.0s median to first token (24h)
GPT-6 Luna5.4s median to first token (24h)
Gemini 3.8 FlashIdle
Updated Sun, 08 Nov 2026 00:55:25 GMT. Checked every 30 seconds. Model figures come from completed hours, so they lag by up to an hour; an idle model has had no requests in the last three hours, which is not the same as being down.