Sage 1.3.0

Levanto LabsDecision model

Sage 1.3.0 by Levanto Labs is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. Hosted, it costs about $0.010 per 1,000 decisions.

Pricing

Input (per 1M tokens)

$0.05

Output (per 1M tokens)

$10.00

Per 1,000 decisions

$0.010

Cost per 1,000 decisions assumes 200 input tokens per decision.

Specifications

Provider: Levanto Labs
Parameters: —
Released: Oct 2026
Open weights: No
Question types: Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism: Hosted API
Backbone: —
Jev-compatible request: Yes
Runs on CPU: —
License: proprietary

Benchmarks

Benchmark Heaven JevBench (Capability): 78.6

Compare Sage 1.3.0 with…

Sage 1.3.0 vs amos-1-large—/1M in Sage 1.3.0 vs amos-1-medium—/1M in Sage 1.3.0 vs Celeris-1 Decision$0.04/1M in Sage 1.3.0 vs ScaleDown Classify-1$0.04/1M in Sage 1.3.0 vs Cloudflare clef—/1M in Sage 1.3.0 vs Cloudflare clef-flash—/1M in

FAQ

How much does Sage 1.3.0 cost?

Hosted, Sage 1.3.0 costs $0.05 per 1M input tokens, about $0.010 per 1,000 decisions at 200 input tokens each.

What questions can Sage 1.3.0 answer?

Sage 1.3.0 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Sage 1.3.0 well calibrated?

No calibration measurement for Sage 1.3.0 is recorded yet.

Is Sage 1.3.0 open weight, and can it run on a CPU?

No, Sage 1.3.0 is closed and served as an API.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Benchmark Heaven JevBench). Pricing is per 1M tokens (USD); confirm with the provider before production use.