Each model is probed with a synthetic request every 20 minutes (Cloudflare cron) · monitoring freeinference.org . Click a model to zoom in on its latency and throughput history.
bge-m3
Status UP
Latency 112 ms
TTFT —
Throughput —
Uptime 100%
Checked 2026-11-07T11:00:13
Latency trend (100) 112 ms · 25–551 ms
click to zoom ↗
deepseek-v4-flash
Status UP
Latency 272 ms
TTFT —
Throughput —
Uptime 97%
Checked 2026-11-07T11:00:13
Latency trend (97) 272 ms · 35–51271 ms
click to zoom ↗
deepseek-v4.1-flash
Status UP
Latency 111 ms
TTFT —
Throughput —
Uptime 38%
Checked 2026-11-07T11:00:13
Latency trend (38) 111 ms · 31–718 ms
click to zoom ↗
glm-5.3
Status UP
Latency 14380 ms
TTFT 3740 ms
Throughput 96.15 tok/s
Uptime 100%
Checked 2026-11-07T11:00:13
TTFT trend (68) 3740 ms · 950–26185 ms
click to zoom ↗
glm-5.3-flash
Status UP
Latency 5201 ms
TTFT 1436 ms
Throughput 70.65 tok/s
Uptime 94%
Checked 2026-11-07T11:00:27
TTFT trend (62) 1436 ms · 137–54380 ms
click to zoom ↗
kimi-k2.7-code
Status UP
Latency 271 ms
TTFT —
Throughput —
Uptime 98%
Checked 2026-11-07T11:00:13
Latency trend (98) 271 ms · 43–14273 ms
click to zoom ↗
minimax-m3.1-flash
Status UP
Latency 113 ms
TTFT —
Throughput —
Uptime 100%
Checked 2026-11-07T11:00:13
Latency trend (100) 113 ms · 30–22439 ms
click to zoom ↗
qwen3.6-35b
Status UP
Latency 273 ms
TTFT —
Throughput —
Uptime 100%
Checked 2026-11-07T11:00:13
Latency trend (100) 273 ms · 50–33869 ms
click to zoom ↗