AI Agent StoreScaleDown · Specialized service
ScaleDown Extract
Pull fields such as invoice numbers, dates and customer names from documents. Describe the fields you want before sending the text.
Catalog added 2026-10-13 UTC · Checked 2026-10-15. Catalog addition and provider launch are separate dates.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: scaledown/extract. The native API reads text or extracts text from supported images and PDFs. Describe fields with a JSON schema or entity descriptions; each match includes a confidence score and surrounding context. The native API returns at most 30 distinct values per entity type; repeated occurrences of one value are grouped. Split work when you need more matches.
Use the exact specialized request format. A normal chat prompt may not supply the fields or document format the service needs.
The selected OpenRouter offer lists 1,000,000 context tokens. These are hosted-service limits, not a verified native API allowance.
OpenRouter lists $0.04 per million input tokens and no output charge. Caching and other fees are unverified. This specialized service has no comparable general-chat quality score. Use actual billed usage and the model named in each response to check your estimate.
Provider release and specifications ↗
Inspect the exact catalog model ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗