SSyncDev

Sage 1.4

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

Levanto Sage 1.4 is catalogued as a point release of Levanto's Sage decision model; no Levanto page confirms version 1.4 yet.

Key specifications

Specification score
14.8
License
Proprietary

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: No version-specific pricing found. Plan-rate billing per token and grounding search; decision answers carry no output charge.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Image input

Produces

  • Decision output

Capabilities

Vision

What is Sage 1.4?

Here is the short version for anyone searching for Levanto Sage 1.4: we could not find it. A registry lists a version 1.4 of Sage dated 4 October 2026, with no hosts attached. No Levanto page we read mentions it. A third-party listing refreshed on 5 October still showed 1.3.0 as current, which sits awkwardly next to a release the day before.

So this page stays deliberately thin. It tells you what Sage is, and how to find out which build you are calling.

What Sage does

Sage is Levanto Labs' hosted decision model. Instead of generating text, it answers a typed question about your content and attaches a probability. Levanto exposes yes/no, choice, scale, sort and tags questions, plus extraction and streaming. When the model cannot decide, it returns null so that your code can escalate.

Checking the version you actually get

The model you select is levanto-sage. That is not a version pin. A response may report a version string such as levanto-sage-v1.3, so log that field on every call. If a 1.4 build is rolled out behind the same ID, your logs will show the switch, and you can compare decision quality before and after.

Practical limits

  • Request size: about 32K tokens, or 128K with extended context
  • Choice options: 2 to 256, or 20 with an image
  • Images (beta): 4 MiB decoded, 8192 px on the longest edge
  • Oversized requests fail; they are never truncated

Cost

Pricing is per token and per grounding search at plan rates, with no output charge on decision answers. We found no version-specific pricing for 1.4.

Our recommendation

Do not plan around a version number that the vendor has not documented. Build against levanto-sage, record the reported version, and keep a labelled regression set of a few hundred cases so a silent model change shows up as a measurable shift. If Levanto later publishes 1.4 release notes, this page will be updated.

For other models in this category, see structured decision models or compare Sage with TypeSafe's Jev.

How to evaluate Sage 1.4

Compare the model on the work you need to complete.

Tasks and inputs

Sage 1.4 is listed for Text classification, Structured Decisions. It accepts text, image and produces decision. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Test labelled examples and choose thresholds from the cost of each error. Validate probabilities against your application’s outcomes.

Choosing a deployment

Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.

Frequently asked questions

We could not confirm it. No Levanto page mentions version 1.4, and the latest documented elsewhere is 1.3.0.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

Google

Gemini Decision 1

Gemini Decision 1 powers Google's Decisions API, returning calibrated yes/no, choice and rubric answers instead of text, at $0.10 per 1M input tokens.

262.14K context

Perplexity

pplx-decider-flash-v1.3

pplx-decider-flash-v1.3 is Perplexity's small, half-price decision model, distilled from the 27B decider, for high-volume classification and span extraction.

— context

Perplexity

pplx-decider-v1.3

pplx-decider-v1.3 is Perplexity's 27B-class decision model: it returns probabilities for choice, yes/no, score and new span-locate questions, not text.

32.77K context

Butler

Cicero

Cicero is Butler Compute's open-weight MoE decision model: up to 64 typed questions per state, a calibrated probability for every option, no text.

131.07K context

Morph

Reflex

Morph Reflex is a family of fast classifier models that label agent turns (jailbreak, looping, frustration and more) with per-class scores.

65.54K context

Sarvam

Sarvam Prism

Sarvam Prism is a 105B decision model that returns calibrated probabilities for yes/no, choice and score questions in English and 10 Indian languages.

131.07K context