{"id":"sage2","slug":"sage2","name":"Sage2","orgId":"levanto-labs","family":"sage2","releaseDate":null,"availability":"ga","openWeights":false,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/levantolabs/status/2117304026911908020","hfRepo":null,"modalities":["text","image"],"aliases":["Sage2","sage 2","levanto sage2","levanto sage 2","levanto-sage-2","sage2 extract","sage2 decide","levanto sage2 extract","levanto sage2 decide"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-03","announced":"2026-11-02","blurb":"Levanto Labs' runtime model for developers, with two modes: Extract turns natural language into typed structured fields, and Decide answers yes/no, choice, scale, sort and tag questions, including over a stream that it reads as the context grows. Hosted API only.","api":"live","apiModelId":"levanto-sage-2","openWeights":"unknown","facts":[{"label":"Modes","value":"Extract (natural language in, typed structured fields out) and Decide (yes/no, choice, scale, sort and tags)"},{"label":"Model ID","value":"Both modes report levanto-sage-2 in API responses"},{"label":"Streaming","value":"Decide can read a conversation or document as it grows over a WebSocket stream (/v1/stream): 1 to 32 questions and up to 16,384 tokens of text and questions per session"},{"label":"Inputs","value":"Text; images in beta"},{"label":"Options","value":"Reasoning, web-search grounding, batch calls and a SystemOne-compatible decision endpoint"},{"label":"Access","value":"Levanto API (sage.levanto.ai) on monthly plans billed per input token, output token and search, with a free plan that includes 20M tokens. Also on NEAR AI and, for agents, through MPP with Stripe cards and Tempo stablecoins"},{"label":"Weights","value":"None announced"},{"label":"Parameters","value":"Not disclosed"},{"label":"Benchmark","value":"Extract Bench v0.1 (1,844 documents from 12 public datasets), built and maintained by Levanto and open-sourced under Apache 2.0"}],"claims":["Lab claim: Extract is 166x cheaper than Opus 5.5 and beats Cloudflare's Clairic.","Lab claim: on Levanto's Extract Bench v0.1, a Sage 2 preview (rc9, fast) scores 77.8 field accuracy and 72.2 on fields not in the document against 75.3 and 59.0 for Clairic.","Lab claim: Decide is 3x faster on progressive context because it reads the context as it grows, with streamed decisions as low as 50 ms; extraction takes about 150 ms of server time on short documents."],"sources":[{"kind":"lab","title":"Levanto Labs announcement on X: Introducing Sage2","url":"https://x.com/levantolabs/status/2117304026911908020","date":"2026-11-02"},{"kind":"lab","title":"Levanto Labs on X: Extract Bench results","url":"https://x.com/levantolabs/status/2117304032255455505","date":"2026-11-02"},{"kind":"lab","title":"Sage2 model page (levanto.ai)","url":"https://levanto.ai/model"},{"kind":"lab","title":"Levanto docs: streaming","url":"https://docs.levanto.ai/stream"},{"kind":"repo","title":"levantolabs/extract-bench on GitHub","url":"https://github.com/levantolabs/extract-bench"}],"firstBenchmark":null},"organization":{"id":"levanto-labs","name":"Levanto Labs","slug":"levanto-labs","country":null,"url":"https://levanto.ai","color":"#A39E8F","mark":"LE"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 2, 2026; no independent results yet.","lead":"As of Nov 22, 2026, Sage2 is pending benchmarks on isitsota: announced Nov 2, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}