Skip to content
All releases
Added

SubQ Snap 1.2

Subquadratic's long-context decision model joins the catalog: 384K context, $0.04 / 1M input, and a tie for first on the Artificial Analysis Decision Index.

subquadratic/subq-snap-1.2 is Subquadratic's long-context decision model. It scores a state and typed questions over text and images, with a 384K-token context, and returns a calibrated probability for every answer. It ties for first on the Artificial Analysis Decision Index at 73, scores 69.05 on the open-source Hugging Face Decision Index, and keeps the same answer when the options are reordered. It is BYOK through SubQ's API at $0.04 per 1M input tokens with free output; new accounts get 100M free tokens.

One request, one yes/no question
const res = await fetch("https://anyrouter.dev/api/v1/decisions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.ANYROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    state: {
      text: "The invoice is 45 days past due and the customer has paid every previous invoice on time.",
    },
    model: "subquadratic/subq-snap-1.2",
    questions: {
      escalate: {
        type: "noul",
        instructions: "Should this invoice be escalated to collections?",
      },
    },
  }),
})
console.log(await res.json())
Run it with the native anyr command
anyr decision --model subquadratic/subq-snap-1.2

More: Decisions app · Decisions API reference · SubQ models docs.

Artificial Analysis Decision Index: SubQ Snap 1.2 scores 73, tied for first
Artificial Analysis Decision Index v2.1. Source: Subquadratic.
Hugging Face Decision Index: Snap 1.2 scores 69.05, ahead of d1-ultra, Snap 1.1 and Jev 1.14
Hugging Face Decision Index. Source: Subquadratic.

Looking for the full catalog? Browse all models.