What every model call cost, and why
A platform that reads documents with models has to answer three questions at any moment: what did this document cost, which model said what, and where did the time go. DocuFlow answers all three from one ledger.
Spend by day, model,
queue and document
Every call is filed against the work that caused it, whether that was extraction, a second reader, a rule asking a question or a reviewer asking the document. Open a trace to read it call by call: model, tokens, cost, latency and why it stopped.
AI cost
Every model call the workspace made: what it cost, how long it took, and what it was for.
Spend
$163.83
last 30d
Model calls
82,565
41 failed
Median call
1.9 s
p95 8.4 s
Tokens in
611.2M
402.9M cached
Tokens out
18.4M
2.1M thinking
Spend per day
Cost of every model call, by the day it was made.
By model
Which model the money went to, and how fast it answers.
| Model | Calls | Median | Cost |
|---|---|---|---|
| gemini-3.1-pro-preview | 18,442 | 6.1 s | $132 |
| gemini-3.8-flash | 41,208 | 1.9 s | $29.80 |
| gpt-oss-120b | 22,915 | 0.9 s | $2.41 |
By kind of work
What the models were asked to do.
Extract aetna-pa-whitfield.pdf
Extraction · pipeline
Cost
$0.0884
Took
16.3 s
Calls
4
Tokens
38.1k / 2.2k
4 calls, in order
- Classify pages1.2 s$0.0021
- Extract fields · page 16.8 s$0.0412
- Extract fields · page 25.9 s$0.0388
- Second reader · 4 low-confidence fields2.4 s$0.0063Modelgemini-3.8-flashvertexTokens6,120 in · 214 out · 5,880 cachedFinished becausestop
Prompt and answer text is not recorded on this deployment.
Counted where
the data lives
Analytics and cost are grouped in the database, so their cost grows with the number of days and queues, not with the number of documents. The headline figure and the breakdown read the same query, so they cannot disagree.
Auto-approved
76%
3,412 of 4,488 approved
Median processing
14.2 s
p95 41.8 s
Documents per day
By final status
Included
Bring the forms your team still retypes
A working session on your own documents: one queue, your fields, your rules, and a count of what would have gone straight through.