SubQ Snap on SubQ API

SubQ Snap · Subquadratic

Serverless

Last refreshed 2026-10-13. Next refresh: weekly.

Why use SubQ Snap on SubQ API?

SubQ API offers SubQ Snap with pay-as-you-go pricing at $0.05/1M input tokens. SubQ API is Subquadratic's API for its own models.

Input / 1M
$0.050
Output / 1M
Free
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: subq-snap-preview
Model ID
subq-snap-preview

Request example

Curated snippets for this provider are not sourced yet. Use SubQ API documentation with model ID subq-snap-preview.

Gotchas

  • Use provider model ID "subq-snap-preview", not the LLMReference slug "subq-snap".

Pricing

TypePrice (per 1M)
Input tokens$0.05
Output tokensFree

Capabilities

VisionMultimodalStructured Outputs

About SubQ Snap

SubQ Snap is Subquadratic's long-context multimodal decision model, built on Subquadratic Sparse Attention (SSA) with a decision head that maps the input to a probability distribution over the allowed answers. It accepts text and up to 4 images per request within a 384K-token (393,216) context window and answers 1–16 named noul (yes/no), choice, or score questions per call. Released 2026-10-12 in public preview on the SubQ Decisions API as subq-snap-preview. Subquadratic reports 61.7 on Decision Index 0.2.1 (vs 57.9 for Jev) and 82.9% on Bespoke Nimble 13; these are vendor-reported. Not a chat model.

Get Started

Model Specs

Released2026-10-12
Context384K