We build Sage, the first decision model, and pioneered multimodality, grounding and reasoning. Benchmark-leading. Ready to deploy in startups and enterprise.
Planet Earth
Joined October 2025
- Tweets585
- Following108
- Followers2.6K
- Likes645
Pinned Tweet
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.
The aeon team has millions of github stars on their security contributions. Glad Sage2 can help with the next million!
@aaronjmars on how Sage 2 by @levantolabs helps Aeon route bug bounties autonomously, flipping as the policy streams in.
xitter.twitterapi.xyz/aaronjmars/status/2117…
Can Sage2 extract all the food mentioned in Chapter 1 of the Hobbit?
Watch @bigironchris demo a live extraction.
This is a tutorial for understanding how to create fields and values for accurate Extractions on documents.
What would you like us to test in the next Sage2 demo?
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.
Decision models are moving into enterprise workflows.
That company data must stay private. Now it can.
Introducing the first private decision model, inside a TEE. Sage is now live on @near_ai’s confidential infrastructure.
Private decisions, at machine speed.
You can call Sage via @near_ai or use private.sage.levanto.ai to get decisions from Sage with a TEE attestation.
Read the blog here:
levanto.ai/blog/sage-near-ai…
7
1,145
Sage powers autonomous agents in @normiesART Arena, a persistent multiplayer world where agents fight, retreat, and form alliances.
The team reports up to 41,000 decisions per hour across 200+ agents.
Read the case study below.
Case Study: levanto.ai/case-study/arena-…
Article: xitter.twitterapi.xyz/normiesart/status/2113…
Been wondering how to use Decision Models in your agent harness?
Introducing Sage Router, in early access on @AntSeed:
- 39% cheaper than Opus at the same accuracy,
- and 31% more efficient than JevRouter
- On OpenRouter's leaderboard (GPQA Diamond), it matches the top router's accuracy at a third of the cost. Benchmarks👇
Now live on the Antseed Network.
We tested the Sage Router on OpenRouter's router leaderboard (GPQA Diamond, 990 questions, at OpenRouter prices):
- Sage Router CQT 3: 93.5%, $0.005 per question
- Jev Router: 93.9%, $0.016
- OpenRouter Auto: 88.2%, $0.009
At our most cost-focused setting, it scores 87.5% at $0.0006 per question, about 26x cheaper than Jev Router.
Full results: levanto.ai/benchmarks
1
7
644
Sage can see images.
This creates novel workflows for video editing.
Instead of using an LLM to review one frame per second of the video, this skill lets you use Sage to analyze frames of a video in milliseconds.
Bad frames get a review from Opus5.5
Sage skill👇
Read this if you make videos with Claude.
I built a skill that cut my QA cost on this video from $127 to 16 cents. It was made with Claude in Remotion.
It's called SageCut. It swaps the LLM out of frame-by-frame QA and uses a multimodal decision model, Sage (@levantolabs), instead.
I'm the only video guy at Levanto. I run 3 Claude plans and have been making Remotion videos since early this year, with BlenderMCP in the mix, so the output is pro-grade with very little babysitting.
The problem: it burned through my Max plan, and a video could take 2 days.
When I dug into the workflow, the reason was that Claude subagents were reviewing every single frame. That cost a ton and added 4+ hours per video.
SageCut hands that step to Sage. Sage is great at spotting defective frames, and only those get passed to Opus 5.5 to fix.
Across 6 A/B tests the output was exactly the same, at 1/10 the QA cost and 1/4 the QA time. On this video, Sage read all 3,153 frames for 16 cents.
If you make Remotion videos, try it.
The link to skill is below.
How long does a Remotion video take you right now with Claude?
Your agent can now confidentially top up its decision model’s balance with ETH, thanks to ZKP.
I just used @MetaMask to pay for decision models, confidentially, with zero-knowledge.
Excited to bring zkAPI by @ethereumfndn and @OpenAnonProject to Sage:
- Deposit ETH once.
- Generate keys with ZK proofs.
- Give a key to your agent.
- Your agent makes decisions, and they can't be linked to the wallet you deposited from.
Play with it 👇
Sage now has servers hosted in the US and the EU.
Companies who want the benefit of decision models in their workflows while staying compliant now have peace of mind.
A gift for my EU friends burdened by GDPR 😅
Introducing Data Residency. Do you need your decision model to be in the EU or the US?
Just call
us.sage.levanto.ai
eu.sage.levanto.ai
Our balancers will do the rest.
You don't care? Just continue to use
sage.levanto.ai
Same API key, same @LevantoLabs tenant.
Enjoy!
6
488
Exciting to see this skill drop from @austingriffith
Sage Wisdom finds where a fast decision model makes your ai product faster, cheaper, safer or better. every swap gets tested before it ships.
Vibecoders delight.
If you like Jev, you'll love Sage
I use it for lots of quick decisions (0.3s)
Gates, routing, moderation, voice commands, etc
SageWisdom is my skill for adding Sage to your apps
Give your agent sagewisdom.bot and let it rip:
Decision models are better at agent orchestration than LLMs.
Check out how @quirq_ai's agentic coding harness uses Sage to route tasks, check completions and optimize spending.
Across 90 tasks, routing with Sage cut costs by 51% ($69.57 → $34.04).
Workflow below 👇
Sage 1.3 is the leading decision model provider via API measured by JevBench.
Yesterday our co-founder @bigironchris demonstrated how to use Sage's multi-modal capabilities to achieve goals in open-world, digital environments.
Models for machines is just beginning.
We’ve *barely* scratched the surface of what decision models can do.
This week we bring you the first-ever World of Warcraft session… played by a decision model.
Watch our Sage play as a dwarf and hit level 5.
📺👇 Full story here: levanto.ai/sagecraft
This is the first decision model to level up a World of Warcraft character.
It died at level 2 😆
Then it learned to heal itself mid-fight. 128+ kills later the dwarf hit level 5, at 2¢ a kill.
The model is Sage, the decision model we build at @levantolabs.
At each step, our harness, SageCraft, hands it a screenshot and a short list of moves. Sage picks one. The harness checks the pick and turns it into keyboard and mouse input.
LLM agents have played games before. They write their own actions. Sage only chooses.
Picking turned out to be the easy part. Sage keeps no memory between calls, so the harness has to carry the goal, what just happened, and what to try when it's stuck.
> 32 sessions, 5h 29m of play, 4,573 decisions
> 103 troggs, 19 wolves, 6 boars
> stuck in one tree long enough that I stopped the session by hand
It wasn't hands-off. A coding agent fixed harness bugs between sessions and helped revive the dwarf while I slept. The last 18 minutes, from late level 4 to 5, ran with no manual input, code changes or restarts.
The video is me narrating it unscripted, watching most of it back for the first time.
This is my first harness build, and as far as I can tell, the first time a decision model is leveling up a live WoW character.
It's open source. The harness and notes on the build are in the first reply below 👇
What do you think could be done better?
Sage is the decision model who can answer ''what-if''
Autoreasoning toggles on when Sage is faced with multi-step logic that can't be handled by other decision models.
Unbefallen explores alternative timelines, see more 👇
Our first uchronia campaign: Waterloo, 1815.
7 historical figures. 1 shared world. Every choice recorded. Play at : unbefallen.com/app/play
Talk to characters powered by Sage from @levantolabs. Collect, trade, build coalitions.
$ELSE now has its first in-game use. More to come.
PerpFlow cut an agentic research workflow from 14 days to 12 hours with Sage, a 28× speedup 🔥
@PerpFlow analyzes markets and sends selected trading signals to subscribers.
The team used Sage to classify 5,972 anonymized market cards against fixed research criteria. The adapter saved the results to files and returned summaries to Claude, keeping thousands of classifications outside its context. Python then evaluated the labels across 85 pre-registered tests.
PerpFlow reached its research conclusion sooner while retaining the requirements for changing its production signals.
Read the Case Study
levanto.ai/case-study/perpfl…
Check out Perpflow
@PerpFlow
3
216
Sage 1.3 scores the highest across decision model benchmarks.
The grounding, reasoning, and vision features enable Sage to reach higher accuracy than other decision models.
Sage classifies data in hours instead of weeks, even when it's messy.
Sage by @LevantoLabs is the first decision model, launched in July, and currently the best on the market.
It wins across all the evals proposed by @perplexity_ai's CEO (nice job @AravSrinivas!), and it's first on JevBench, beating Jev and Google's models on every dimension.
BUT frankly, benchmarks are not what excites us.
I'm BORED by the dozens of new decision models launching every day with a tiny +0.02 on some eval. They all look the same.
The magic is somewhere else.
There are thousands of new things that could be invented in the space of decision models and models for machines. The invention space is huge!
After launching Sage, we also pioneered:
- The first guardrails and model routers built on decision models
- Automated context engineering with "grounding" (automatic web search when confidence is low). Decision models are only as smart as their context, especially because they can't make tool calls.
- Reasoning. In many use cases you don't know whether your question is System 1 or System 2. With reasoning, the model is as fast as a System 1 model when the question is System 1, and takes more time when it's needed. This enables hard, multi-step decisions. Our clients just want the correct answer, and in some use cases they're happy to wait 0.5s more. This will soon become the market standard (GLiDE/@george_onx and @TypeLLM already followed).
And *so* much is yet to come. Models for machines: it's just the beginning!
We're cooking. Follow @levantolabs for new product primitives that will surprise you.
Open innovation is HEALTHY.
Competition is HEALTHY.
Benchmark-race is BORING.
Product inventions are FUN.
Go go go!!!
