Analytics

Public & anonymized. Same page for everyone, no account needed. Rows hold shape, never identity: no ip, no cookie id, no user id, no answer text. Cells under 7 observations stay hidden. How this data works · JSON

un (continuing education) · Last 28 days · computed 2026-11-14 17:17 UTC · refreshes every few minutes

2399 Model & service calls

85.4% Succeeded

1s Median latency

2.5 Calls per graded answer grading purposes only

317554 Characters sent

665 Characters received

Every outbound call to a language model, the decision classifier, translation, speech, lesson generation or code execution. Purpose, host, latency & outcome only. No prompt or completion text.

By purpose

Purpose	Calls	Share	Succeeded	Median	95th	Chars in	Chars out
Text to speech	2392	99.7%	85.3%	1s	2s	304277	0
Classification (chat model)	2	0.1%	100.0%	1s	1s	8675	68
Feedback	2	0.1%	100.0%	2s	2s	3419	419
Code execution	1	0.0%	100.0%	1s	1s	11	0
Speech to text (mic)	1	0.0%	100.0%	0s	0s	0	31
Rubric scoring	1	0.0%	100.0%	1s	1s	1172	147

By lesson

Which lessons drove model calls — chat, feedback and speech attributed to the lesson the learner was on.

No lesson-attributed calls yet.

By endpoint

Host	Calls	Share	Succeeded	Median
speech.ai.unturf.com	2393	99.7%	85.3%	1s
qwen.ai.unturf.com	4	0.2%	100.0%	1s
unsandbox	1	0.0%	100.0%	1s
hermes.ai.unturf.com	1	0.0%	100.0%	2s

By model

tts-1-f5 2392 (99.7%)

turboderp/Qwen3.8-27B-exl3 5 (0.2%)

python 1 (0.0%)

stt-1-parakeet 1 (0.0%)

By brand

un (continuing education) 2399 (100.0%)

Calls over time

Failed calls over time

Calls over time by purpose

Calls: classify

Calls: feedback

Calls: rubric

Calls: tts

Failure reasons

HTTP 401 308

unavailable 21

HTTP 429 12

ReadTimeout 4

HTTP 503 4

HTTP 502 2