AI Agent StoreScaleDown · Specialized Gateway service
ScaleDown Classify-1
Assign text to your own labels, such as sales, support or billing, and receive a probability for each label.
First reviewed 2026-10-14 · Checked 2026-10-15. The launch date has not been confirmed.
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 AI Gateway route ID: scaledown/scaledown-classify-1. The provider supports custom labels with rubrics and a separate fixed-answer Decisions API. This profile covers the Gateway Classify-1 offer; general chat scores do not establish classification accuracy. In the native classification API, the optional explanation is a second call enabled by default, with its input billed at twice the base rate. It explains the chosen label; it is not an independent second opinion. Gateway’s exact handling of that option is unverified.
Test examples with known labels, especially ambiguous cases that should go to a person. A high confidence score alone does not establish that an answer is correct.
Gateway lists $0.05 per million input tokens and free output. Its zero capacity fields do not establish a usable zero-token limit; request limits, caching and other fees are unverified. Use actual billed usage and the model named in each response to check your estimate.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
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 ↗