Levanto Sage

Name: Levanto Sage
Author: Levanto Labs

Last refreshed

2026-10-05

Status

Researched 1d ago

ProprietaryCommercial use: conditionalMultimodalAgentsVisionJSON / Tool useAgent

Specifications

Family: Levanto Sage
Context: 32k
Openness: Proprietary
License: ProprietaryCommercial use: conditional
Weights: Not released
Code: Unknown

Created by

Levanto Labs

Website

Pricing

Output / 1M

$10.00

Input / 1M

$0.050

Cheapest of 1 route · Levanto

Providers(1)

Levanto

View 1 provider route

Links

Website

About

Sage (current version 1.3.0, API model levanto-sage-v1.3) is Levanto Labs' hosted decision model. Through POST /decide and /decide/batch it answers yes/no, choice (up to 120 options), scale (2–26 levels against a rubric), sort, and tags questions about text, lists, or images (beta). It returns a typed answer with a probability, or null when it isn't sure, so workflows can route uncertain cases to a person. Optional reasoning lets Sage think a hard question through, within 10 seconds per answer, and optional grounding searches the web first. A Jev-compatible SystemOne endpoint is also documented.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
Levanto	$0.050	$10.00	Serverless

Capabilities

VisionMultimodalReasoningStructured Outputs

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.