# Levanto launches Sage2, a streaming decision and extraction model

> Original title: This is a new streaming decision model:

- Source: Santiago
- Published: 2026-11-02T18:06:47.000Z
- Bad Influence: https://badinfluence.news/items/u94q8dns2l9nx6jjwaprmrg2i
- Original: https://x.com/svpino/status/2117317513105313904

## Summary

Levanto's Sage2 is a new model that answers questions about input text with a confidence score, updating its answers as the text streams in, 3x faster. The same endpoint also extracts structured data from text in about 150 ms, which Levanto says is 75x cheaper than Opus 5.5 on document extraction. Levanto is offering 20M free tokens to start.

## Post

This is a new streaming decision model:

• Give it text + list of questions
• It answers back with a confidence score
• Answers update as the text arrives, 3x faster

But it's also an extraction model:

• Text in, structured data out
• ~150 ms per extraction
• Claims 75x cheaper than Opus 5.5 on document extraction

It all uses the same endpoint. They are offering 20M free tokens to start.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2117317490472886272%2Fimg%2Ft_K2YkOfd54USil6.jpg&mode=thumb&exp=1793836800&sig=7f36814912f77c03)

## Quoted post @levantolabs

> Software can now understand human language and act on it, in real time.
> 
> Introducing Sage2
> - Extract: natural language in, structured data out. 166x cheaper than Opus 5.5, beats @Cloudflare's Clairic
> - Decide: the first decision model with streaming. 3x faster, because it reads the context as it grows.
> 
> Sage2 is a new primitive for developers. Get 20M tokens free 👇
> 
> Also available on @near_ai and, for agents, via @mpp with @Stripe cards and @Tempo stables.

https://x.com/levantolabs/status/2117304026911908020