The cheapest model that clears your bar

Which model is the cheapest that still gets it right? Find out on your own data.

Bring 50-300 examples and your OpenRouter key. Get one named model, its cost per successful task and the failures it will have, before you switch.

Get a verdict on my examples   Read the live verdicts

Two verdicts, run on public data

Classification · 150 public examples

meta-llama/llama-3.3-70b-instruct

Matches openai/gpt-4.1 on Banking customer-message intent classification (77 intents), at a fraction of the price.

$0.000082per successful task
93.4%under openai/gpt-4.1 ($0.001235)
77.3%pass rate vs 76.7% for the baseline

See the numbers and failures

JSON extraction · 150 public examples

mistralai/mistral-small-3.2-24b-instruct

Matches openai/gpt-4.1 on Structured JSON extraction from messy documents, at a fraction of the price.

$0.000203per successful task
96.1%under openai/gpt-4.1 ($0.005173)
62.7%pass rate vs 62.0% for the baseline

See the numbers and failures

Each page shows the full table, 150 examples, the failures, the price snapshot date and a script that re-runs it.

What you get for a run

  1. Your examples, your bar. Upload input/expected pairs and set the pass rate you need.
  2. Real cost per successful task. Retries and failed attempts are priced in, not just tokens.
  3. A paired answer. The cheapest model that matches your current one on the same tasks, with the failures to read.
  4. Payback in days. The saving at your monthly bill against the price of the run.

Get this verdict on your own examples

Bring 50-300 input/expected pairs and your OpenRouter key. You get one named model, its cost per successful task and the failures it will have.

Pro run

$19 per run

  • Up to 150 of your examples
  • Up to 8 models plus your current one as the baseline
  • Verdict with cost per successful task, retry tax, failures and payback

We'll email you the day it opens. No payment now. Privacy

Deep run

$49 per run

  • Up to 300 of your examples
  • Up to 15 models plus your current one
  • 3 re-checks within 30 days when prices or models move

We'll email you the day it opens. No payment now. Privacy

Model watch

$9 per month

  • Your finalists re-checked when OpenRouter prices or models change
  • A dated change list: who got cheaper, who now clears your bar
  • Cached results reused, so only new or repriced cells run

We'll email you the day it opens. No payment now. Privacy