// OBSERVATORY

Inference, in numbers.

A view into the requests, models, and tokens moving through the API.

BACK TO THE API GUIDE ↗

Live usage for inference.lulzx.space. Counting since 2026-09-05T16:49:54.158044+00:00 · last request 2026-09-05T17:53:45.245858+00:00.

Requests2920 succeeded
Success rate69.0%of all requests
Total tokens1.6k1.4k in / 200 out
Median latency1.09 sp95 3.88 s
p99 latency5.24 sover 11 samples
Throughput47.6 tok/smean output rate
Time to first token1.15 s1 streamed
Unique callers11 live tokens

Requests per hour · last 24 hours

No data yet.

Requests per day · last 14 days

No data yet.

Tokens per day · last 14 days

No data yet.

Input tokens Output tokens

Requests by model

minimax-m37
gemma-4-31b-it1
minimax-m2.71
nemotron-3-super-120b-a12b1
nemotron-3.5-lightning1

Response status

2009
4292

Transferred 1.3kB in / 11.1kB out.

Model performance

ModelRequestsTokensAvg latencyTok/sSuccess
minimax-m371k1.72 s60.286%
gemma-4-31b-it10220 ms0.00%
minimax-m2.71852.18 s18.3100%
nemotron-3-super-120b-a12b160840 ms47.6100%
nemotron-3.5-lightning1601.09 s36.8100%

Recent requests

Time (UTC)ModelStatusLatencyTok/s
2026-09-05 17:53:45minimax-m32005.58 s0.9
2026-09-05 17:46:16minimax-m32001.18 s394.8
2026-09-05 17:46:14minimax-m3200990 ms10.1
2026-09-05 17:45:54minimax-m32001.02 s2.0
2026-09-05 17:45:52gemma-4-31b-it429220 ms0.0
2026-09-05 17:44:24minimax-m32001.51 s5.3
2026-09-05 17:44:22minimax-m3429555 ms0.0
2026-09-05 17:44:21nemotron-3.5-lightning2001.09 s36.8
2026-09-05 17:44:19minimax-m2.72002.18 s18.3
2026-09-05 17:44:16nemotron-3-super-120b-a12b200840 ms47.6
2026-09-05 17:44:15minimax-m32001.22 s8.2

Zero prompt and response retention on this gateway. Usage counts and operational metrics only.