SubQ Snap
Long-context decision model with typed answers and probabilities
SubQ Snap is Subquadratic's decision model. Given a state (text, with images as input) and typed questions (yes/no, choice or score), it returns a probability for every option instead of generated text. The current version, Snap 1.1, is in public preview with a 384K-token context window.
It runs on the SubQ API's Decisions endpoint at $0.04 per 1M input tokens, output free, and new users get 100M free tokens. Subquadratic Inc. is a Delaware corporation based in Miami, Florida.
Pricing: Per token usage
Choosing a decision model right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a decision model right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
SubQ Snap prices by model
Per 1M tokens, read off SubQ Snap's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| SubQ Snap 1.1 | $0.04 | โ | $0.00 | 25 Oct 2026 | Public preview. Output tokens are free; 100M free tokens for new users. |
SubQ Snap Alternatives
Explore 152 products in the Inference APIs category. View all SubQ Snap alternatives.
Kev
Open decision models from 0.8B to 27B, built on Qwen and compatible with TypeSafe's Jev API.
Laya
Open-source multilingual decision model: typed choices, scores and yes/no answers in one forward pass.
Bespoke Nimble
Hosted and open decision models that return a probability for every answer
Work on SubQ Snap? Feature it at the top of Inference APIs.
Is your product missing?