Usage Statistics

Historical request usage loaded from the Docker-mounted telemetry log. Choose a time window and the model profiles to include.

Models included (1 / 6 selected)
GB10_11 model
GB10_1_openai4 models
NVIDIA 50901 model
Showing 16,056 requests from 2026-09-23 16:40 through 2026-11-22 00:33. Averages exclude zero-valued observations/buckets. Dashboard Reset does not delete this retained history. Per-model Clear resets a live model's usage or removes a historical-only entry from the selector; the retained file and global all-time totals are never rewritten. History file: /persist/data/token-events.jsonl
Requests
16,056
587 errors ยท 713 missing usage
Input Tokens
3,974,076,786
prompt/input usage
Output Tokens
7,424,942
generated/completion usage
Avg Duration
14.23s
TTFT 7.70s average
Avg Output Rate
115.7
tokens/sec during active generation

Requests

Completed requests, errors, and requests without upstream usage data.

requestserrorsmissing usagerequest avg 2.01K reqerror avg 73.38 reqmissing avg 89.13 req
4.33K req0 req
09-23 16:4011-19 16:40

Input Tokens

Prompt/input tokens consumed in each time bucket.

input tokensavg 496.76M tok
1382.45M tok0 tok
09-23 16:4011-19 16:40

Output Tokens

Generated/completion tokens produced in each time bucket.

output tokensavg 928.12K tok
1.86M tok0 tok
09-23 16:4011-19 16:40

Latency

Average end-to-end request duration and time to first token.

durationTTFTduration avg 14.23 sTTFT avg 7.70 s
30.52 s0 s
09-23 16:4011-19 16:40

Generation Throughput

Output tokens divided by active generation seconds for each bucket.

output tok/savg 115.7 tok/s
207.4 tok/s0 tok/s
09-23 16:4011-19 16:40

Breakdown by Model

SystemModelRequestsErrorsInputOutputTotalAvg durationAvg TTFTAvg tok/s
GB10_1_openaigb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keys
gb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keys
16,0565873,974,076,7867,424,9423,981,501,72814.23s7.70s115.7