AI Agent StoreScaleDown · New hosting option
ScaleDown Extract-1 · Gateway
Extract fields from a document using the structure you define, such as invoice amounts or contract parties.
First reviewed 2026-10-21 · Checked 2026-11-03. Gateway dates this offer October 20. This does not establish a new underlying checkpoint.
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 records with known answers, including cases that should go to a person.
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 AI Gateway route ID: scaledown/scaledown-extract-1. Provider documentation declares text input and no tool-calling entry.
This is a new Gateway offer for an existing specialized model. Use the full service ID; native API limits and document-processing features may differ.
Gateway declares one million context and output tokens. The native extractor separately limits distinct values per entity type; do not interpret the hosted output allowance as a promise of one million useful extracted tokens.
Gateway lists $0.05 per million input tokens and zero output-token charge. No cache rate is verified. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
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 ↗