SuperCosmos 2.0
SuperCosmos 2.0 Flash
The fastest SuperCosmos 2.0 effort. Thinks briefly; quick answers, tool loops, images and documents.
Flash is the fastest SuperCosmos 2.0 effort. It thinks briefly before it answers, so each step comes back quickly, and it reads images and documents like every 2.0 effort. It's the right default for high-volume and interactive work.
| Display name | SuperCosmos 2.0 Flash |
| Model id | supercosmos-2-flash |
| Model | SuperCosmos 2.0: 1T parameters |
| Context window | Up to 1M tokens (1,048,576) |
| Max output tokens | 32,768 |
| Input | Text, images and files |
| Agent API | "tier": "flash" (also what auto runs bill as) |
| Input price | $1.80 per 1M tokens |
| Output price | $4.20 per 1M tokens |
| Long context | Long-context input above 262K tokens: 1.5× |
Good fits
- Quick answers and small, well-described changes
- Tool loops where many short steps add up
- Reading a screenshot, a chart or a PDF
- Extracting data into strict JSON
Move up when
A task needs a plan across several files, keeps failing its own checks, or the answers miss the point. Try Max.
Was this page helpful?