A sample savings report

This is the page you get back. It uses our own test jobs, not a customer's.

Savings reportSample · tested Nov 13, 2026 · today's model: Claude Sonnet 5.5
Today$258.53a month
After$11.04a month
You save$247.4995.7% lower

The short answer

Switch four jobs. Keep one where it is.

JobRuns a monthTodayCheapest model that passedAfterTestAnswer
Monitoring every 15 min2,880$119.52gpt-oss-120b$1.5210 of 10Switch
Ticket tagging 50 batches a day1,500$63.14gpt-oss-120b$0.6910 of 10Switch
Status check every 30 min1,440$57.57DeepSeek V4 Pro$2.6510 of 10Switch
Daily briefing once a day300$12.24gpt-oss-120b$0.1210 of 10Switch
Inbox digest once a day150$6.06None passed every run$6.069 of 10 and 7 of 10Keep
A month$258.53$11.04You save $247.49

Why the inbox digest stays

This job decides which emails need action. The two cheaper models passed 9 of 10 and 7 of 10 runs. A job only switches when a model passes every run, so this one stays on Claude Sonnet 5.5.

One thing to know before you switch

The cheaper models were slower: 6 to 8 seconds an answer, against about 2.4. That is fine for background jobs. It is not fine for anything a person waits on.

How we tested

Each job ran 10 times on each cheaper model, across two hosts, with the same instructions and inputs. Code graded every answer. No model graded another model. In your report, the answer key is what your current model already said. Read the full test.

What happens next

You change one setting per job. If the report finds less than $50 a month to save, it says so and tells you not to bother.

About this sample: five test jobs written by Bitdepth, short and without tool calls. It is a small test. Real jobs can pass at different rates, which is why your report runs on your own.

Numbers against a stated reference. Not a claim about intent.Listed prices from OpenRouter, read nightly; grades are Bitdepth's.