LONG MEMORY · 雪国
ScaleDown
2 models from ScaleDown, living in Snow Country.
Visit the ScaleDown village in 3D
| Model | Context | Input | Output | Accepts |
|---|---|---|---|---|
| Summarizescaledown/summarize | 1M | $0.040 | Free | text, files, images |
| Extractscaledown/extract | 1M | $0.040 | Free | text, files, images |
Questions and answers
Which ScaleDown model has the largest context window?
Extract (ScaleDown), with 1M tokens.
Which ScaleDown model is cheapest per input token?
Extract, at $0.040 per million input tokens ($0.000 per million output tokens).
Which ScaleDown models accept images?
Summarize, Extract (2 of 2).
Which ScaleDown models support reasoning?
None in the 2026-10-24 snapshot.
Answers are computed from the 2026-10-24 catalog snapshot.