Volurynt

Kestrel Labs / Production / Usage

Usage analytics

Demonstration data · last event Oct 18, 2026, 14:22 UTC

Demonstration data · last event Oct 18, 2026, 14:22 UTC

Last 30 days

compared with the prior 30 days

Requests

1.62M

+29.2%

×

Tokens per request

2,393

+2.1%

=

Tokens

3.87B

+32.0%

Token anatomy

Input 3.09B

1,909 per request

+1.4%

Output 781.75M

484 per request

+5.0%

Output is 20.2% of tokens, up 0.5 pts on the prior 30 days.

What moved tokens

Prior

2.9B

More requests

+856.7M

Heavier requests

+81.0M

Now

3.9B

Tokens rose 937.8M. Request volume did most of it: +856.7M from more requests, +81.0M from heavier requests.

Daily volume

Average day

53.9K requests

Average day, tokens

128.94M

Peak day

Oct 12 · 76.2K

Days in window

30

01

Request and token traffic

Switch between requests, tokens, input against output, and tokens per request. Drag across the chart to analyze a window; everything below follows it.

Switch between requests, tokens, input against output, and tokens per request. Drag across the chart to analyze a window; everything below follows it.

1.62M requests, +29.2% on the prior 30 days. Claude Sonnet 4.5 leads with 42%.

Output anomaly

Drag across the chart to analyze a window.

Drag across the chart to analyze a window.

02

Token anatomy by model

Input and output tokens per request for each model, against the prior window. Select a model to focus the page on it.

Model

← Input per request

Output →

Prior window · 3.09B input and 781.75M output tokens in total · Select a model to focus the page.

03

Model share shift

How request and token share moved between models, and how concentrated usage has become.

Prior → current

PRIORNOW40.1
42.0%+2.0
Usage analytics · Volurynt
17.3
15.7%−1.6
Usage analytics · Volurynt
22.1
21.2%−0.8
Usage analytics · Volurynt
20.5
21.0%+0.5
Usage analytics · Volurynt

Effective models · requests

3.44

Usage is spread as if across 3.4 equally used models. Prior: 3.55.

Mix now

Top bar: now · thin bar: prior

Token weight

token share ÷ request share

Claude Sonnet 4.5

×1.24

GPT-4o

×0.93

DeepSeek V3

×0.90

Gemini 2.5 Flash

×0.68

Above ×1.00 a model uses more than its share of tokens per request. The tick marks parity.

04

Where usage comes from

Split consumption by calling workload or by API endpoint. Select a segment to filter the whole page to it.

Search and retrieval lost 0.9 pts of tokens share on the prior 30 days.

43.8%

Code review agent

22.8%

Support copilot

17.4%

Nightly summaries

16.0%

Search and retrieval

Workload

Requests

Tokens

Per request

Change

Daily requests

Model mix

Tokens

4 workloads · 1.62M requests · 3.87B tokens.

Select a segment to filter the page.

05

Patterns and anomalies

Findings computed from the usage data, each with the series it came from. Inspect one to scope the page to its window.

Daily requests

30 days

Low

High

Output anomaly

Average by weekday

Last 30 days

Mon

64.6K

Tue

59.9K

Wed

61.4K

Thu

60.6K

Fri

62.5K

Sat

36.7K

Sun

39.4K

Investigation queue

6 findings · Last 30 days

Investigate

Claude Sonnet 4.5

Claude Sonnet 4.5 answers ran +72% longer

Output averaged 970 tokens per request on Oct 12, against a 7-day baseline of 563. Support copilot produced all of the extra 25.3M output tokens (Oct 12–13).

+72%

output per request

Investigate

Claude Sonnet 4.5

Claude Sonnet 4.5 answers ran +72% longer

Output averaged 970 tokens per request on Oct 12, against a 7-day baseline of 563. Support copilot produced all of the extra 25.3M output tokens (Oct 12–13).

+72%

output per request

Watch

Traffic stepped up from Sep 24

Requests averaged 55.4K a day in the week from Sep 24, +25% on the week before. The higher level has held: the latest 7 days averaged 58.6K.

+25%

week on week

Watch

Traffic stepped up from Sep 24

Requests averaged 55.4K a day in the week from Sep 24, +25% on the week before. The higher level has held: the latest 7 days averaged 58.6K.

+25%

week on week

Watch

Claude Sonnet 4.5

Claude Sonnet 4.5 gained 2.0 pts of request share

It handled 42.0% of requests, up from 40.1% in the prior 30 days. Its token share moved from 49.8% to 52.2%.

+2.0

share points

Watch

Claude Sonnet 4.5

Claude Sonnet 4.5 gained 2.0 pts of request share

It handled 42.0% of requests, up from 40.1% in the prior 30 days. Its token share moved from 49.8% to 52.2%.

+2.0

share points

Pattern

Claude Sonnet 4.5

Claude Sonnet 4.5 carries 52% of tokens

Token usage is spread like 2.9 equally used models (3.0 in the prior 30 days). Usage is concentrating on fewer models.

2.9

effective models

Pattern

Claude Sonnet 4.5

Claude Sonnet 4.5 carries 52% of tokens

Token usage is spread like 2.9 equally used models (3.0 in the prior 30 days). Usage is concentrating on fewer models.

2.9

effective models

Pattern

Weekends run at 62% of weekday volume

Nightly summaries are 34% of weekend requests and 12% on weekdays, so weekend traffic leans toward batch work.

62%

weekend vs weekday

Pattern

Weekends run at 62% of weekday volume

Nightly summaries are 34% of weekend requests and 12% on weekdays, so weekend traffic leans toward batch work.

62%

weekend vs weekday

Pattern

Busiest day: Monday, Oct 12

76.2K requests and 192.7M tokens. On an average weekday the busiest hour is 15:00 UTC, with about 4.1K requests.

76.2K

requests that day

Pattern

Busiest day: Monday, Oct 12

76.2K requests and 192.7M tokens. On an average weekday the busiest hour is 15:00 UTC, with about 4.1K requests.

76.2K

requests that day

06

Usage records

Daily records per model and workload, the same grain as a provider usage export. They sum exactly to the totals above.

1–12 of 480 records · 1.62M requests · 3.87B tokens · $13,825 · matches the window totals

Create a free website with Framer, the website builder loved by startups, designers and agencies.