How many AI models does ScaleDown serve?
2 tracked models as of 7 November 2026: 2 language models, across 2 live endpoints observed through OpenRouter.
Inference provider
ScaleDown: AI models and API pricing
Every tracked model ScaleDown serves through OpenRouter, with ScaleDown's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.
Snapshot as of 7 November 2026
ScaleDown serves 2 tracked models through 2 endpoints as of 7 November 2026; mean measured uptime is 91.67%.
Models served
2
On the ModelCap Index
0
Cheapest output price
—
Language models on ScaleDown (2)
Ranked models first, in ModelCap Index order. Prices are the lowest ScaleDown lists for the model; the endpoint count shows how many deployments carry it.
ScaleDown on ModelCap: common questions
What is the best model available on ScaleDown?
None of the ScaleDown models currently holds a public ModelCap Index position; the table lists them alphabetically.
What is the cheapest model on ScaleDown?
ScaleDown lists no positive language-token price in the current snapshot.
Which ScaleDown model has the largest context window?
Extract, served with a 1M-token context window on ScaleDown. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is ScaleDown?
Mean measured uptime across ScaleDown endpoints is 91.67% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.
Where do the ScaleDown prices come from?
From the OpenRouter catalogue entry for each ScaleDown endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where ScaleDown exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.
How current is this page?
This page uses the published ModelCap snapshot dated 7 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.