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
Verdict library
Each verdict runs the same examples through 8 models, counts every retry in the price and names the cheapest one that matches the baseline. The dataset, the prompt and a re-run script are on the page.
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.
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.
Prices and models move every month. Leave your email and we'll send a note when a verdict here changes. One short email per change. Or follow the feed.
Used only for these notes. Privacy
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.
$19 per run
We'll email you the day it opens. No payment now. Privacy
$49 per run
We'll email you the day it opens. No payment now. Privacy
$9 per month
We'll email you the day it opens. No payment now. Privacy