Freemium
Added on Nov 09,2026
Sage2 is a decision and extraction model from Levanto Labs that software can call at runtime to get typed answers with a calibrated confidence score.
Instead of hard-coding rules such as regular expressions, a running program sends text and a question to Sage and continues based on the answer. If Sage is unsure it returns null, so your code knows when to hand a case to a human.
Key features include a decide endpoint for yes/no, choice, scale, tags and sort questions, a streaming WebSocket endpoint where the answer updates as text arrives, and an extract endpoint that turns text into structured fields such as money amounts. It also supports batching, reasoning, image inputs and web search from the same API key.
Levanto reports a median latency of around 330 ms and an accuracy of 93.9% for Sage v1.1 on 213 public JevBench tasks, with per-decision costs well below general frontier language models on the same questions.
Example uses on the site include detecting personal information in documents, spotting refund requests, deciding when a support conversation needs escalation, moderating posts with tags and extracting invoice fields.
Levanto also published SageCraft, a free open-source research framework under Apache 2.0 in which Sage plays World of Warcraft from screenshots and keystrokes, with recorded decisions and replay tools on GitHub.
Pricing: a Free plan includes $1 of usage a month. Paid plans are Developer at $14 per month, Starter at $49, Pro at $99 and Growth at $249, each including the same amount of usage. Input is priced from $0.05 per million tokens and output at $1 per million tokens, with web search at $0.10 each.
It is suited to developers and teams building agents, workflows, support tooling and data pipelines that need fast, low-cost decisions inside their code.
By the PowerfulAI.tools Editorial Team · Updated 10 November 2026 · Researched with AI assistance and checked against the official Sage2 website · How we review tools
Free plan includes $1 of usage a month; paid plans cost $14, $49, $99 or $249 per month, each including that amount in usage, with input from $0.038 to $0.05 per 1M tokens.
Pricing checked against the official Sage2 website in November 2026. Prices can change, so confirm before you buy.
Developers who want their software to make semantic decisions at runtime, such as flagging personal information or moderating posts, without calling a full LLM.
Yes. The listed website now presents the product as Sage, a decision model API from Levanto Labs.
No. Plans have no seats and no overage invoices, and unused usage does not roll over.
Popular alternatives to Sage2 include Pollinations, NemoClaw and Agnes AI. Compare their pricing and what each is best for below.
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| OrcaRouter | Freemium | Developers and teams who want to balance AI quality and cost across many models. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
Own Sage2? Add this badge to your website.
Leave a review for the community
No Review Found
