正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Reason: A state-of-the-art harness on cost efficiency Beats Codex+Astra on frontier benchmarks while being 22% more cost effective. Try it for free today

Adi Singh

2,332 subscribers

24,643 次观看 • 15 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

23 条评论

Yash 的头像

Yash15 天前

Any pricing page which gives a proper usage allotment? Couldn't find anything, even the docs seem to be limited to the API

Adi Singh 的头像

Adi Singh15 天前

All can be found in the app!

Yash 的头像

Yash15 天前

There's nothing beyond this SS. No idea as to what configuration of VM this is supposed to correspond to, or if we can extrapolate from that for other sizes, or if any inference is included, or whether they are interchangeable. Also, a public pricing page should be providing these details

aloha 的头像

aloha15 天前

Highly recommend!

Pratik 的头像

Pratik15 天前

banger video!

Adi Singh 的头像

Adi Singh15 天前

Thanks!

shakil 的头像

shakil15 天前

trying to use deepseek in the CLI using API. Unable to find it. Can you help?

Adi Singh 的头像

Adi Singh15 天前

Totally. Can you send me more info in the slack?

棗（なつめ）@フリーランス的头像

棗（なつめ）@フリーランス15 天前

codex専用ですか？

Adi Singh 的头像

Adi Singh15 天前

You can use codex in it!

Aaliya 的头像

Aaliya15 天前

Getting strong results while spending less is always good.

Adi Singh 的头像

Adi Singh15 天前

Ofc

3.14159... 的头像

3.14159...15 天前

Taking it for a spin today

Adi Singh 的头像

Adi Singh15 天前

its an honor mr pi

Kanes 的头像

Kanes15 天前

i'll wait for windows app version

Adi Singh 的头像

Adi Singh15 天前

Use it in the cli!

TouchingGrass 的头像

TouchingGrass15 天前

Can I run it locally/offline e.g if I have a local model? Also is the app fully local? Or is it cloud based?

catman 的头像

catman15 天前

A better harness is like a more efficient workshop: benchmark wins matter, but the real test is whether the same quality takes fewer tokens and tool calls on your workload.

nmz 的头像

nmz15 天前

Your bullshit logo looks like Grok bot dawg... just stop it while you can

Franco Jalil 的头像

Franco Jalil15 天前

nice

Yashraj Dudhe 的头像

Yashraj Dudhe15 天前

Why is ther a download for mobile/windows which when clicked only shows get for mac??

God's Eye Preview 的头像

God's Eye Preview15 天前

Looks incredible!

squidlee 的头像

squidlee15 天前

just the harness right?

相关视频

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

NVIDIA AI

12,152 次观看 • 7 个月前

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Databricks

126,791 次观看 • 2 个月前

Introducing Reason 1.0 A frontier coding agent for valuable work. We wanted to see what a good coding agent would look like. Seamless, simple with customization for your models and subscriptions. Fast and lightweight, Reason Scores incredible on standard benchmarks. Use it for free today

Introducing Reason 1.0 A frontier coding agent for valuable work. We wanted to see what a good coding agent would look like. Seamless, simple with customization for your models and subscriptions. Fast and lightweight, Reason Scores incredible on standard benchmarks. Use it for free today

Adi Singh

49,368 次观看 • 23 天前

Introducing NDI 1.0 - a small model for document processing. #1 on Parse Index Normalized (across 6 public benchmarks) GPT-6 Astra performance at 1/10th the cost 📈 Trained on 15M+ financial files for industry-grade accuracy. Get started with $25 in free credits: Reply "NDI" for a single file setup for Claude Code, Codex, PI, Opencode, Hermes, Prime Agent, and more. Start parsing and classifying documents.

Introducing NDI 1.0 - a small model for document processing. #1 on Parse Index Normalized (across 6 public benchmarks) GPT-6 Astra performance at 1/10th the cost 📈 Trained on 15M+ financial files for industry-grade accuracy. Get started with $25 in free credits: Reply "NDI" for a single file setup for Claude Code, Codex, PI, Opencode, Hermes, Prime Agent, and more. Start parsing and classifying documents.

Nace AI

1,307,675 次观看 • 20 天前

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.

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.

Levanto Labs

34,059 次观看 • 9 天前

Introducing the Morph Model Router. It chooses the best model for each task in under 50ms. Keep frontier performance while lowering latency and cost. Available today in our API

Introducing the Morph Model Router. It chooses the best model for each task in under 50ms. Keep frontier performance while lowering latency and cost. Available today in our API

Morph

20,281 次观看 • 4 个月前

Introducing Shift-1, a frontier coding router trained on AC2 that reduced coding agent cost by up to 55% with no noticeable drop in quality. Try it at

Introducing Shift-1, a frontier coding router trained on AC2 that reduced coding agent cost by up to 55% with no noticeable drop in quality. Try it at

Applied Compute

49,222 次观看 • 7 天前

Introducing Harness-1, a 20B search agent trained with a state-externalizing harness. > frontier-level long-horizon search, rivaling Opus-4.6 and outperforming GPT-5.4 > Context-1-level cost and latency > externalizes candidates, evidence, verification, and search history > open-source

Introducing Harness-1, a 20B search agent trained with a state-externalizing harness. > frontier-level long-horizon search, rivaling Opus-4.6 and outperforming GPT-5.4 > Context-1-level cost and latency > externalizes candidates, evidence, verification, and search history > open-source

Patrick Jiang

290,147 次观看 • 4 个月前

Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus. /agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.

Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus. /agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.

Exa

1,074,567 次观看 • 4 个月前

Introducing OpenSource Free WebAccess - 100% FREE Web search & fetch TinyFish - Any web page & data, agent can access - Routing each request to the vendor best at that task - Benchmark on cost/speed/token-efficiency Try it at Repo link below 👇

Introducing OpenSource Free WebAccess - 100% FREE Web search & fetch TinyFish - Any web page & data, agent can access - Routing each request to the vendor best at that task - Benchmark on cost/speed/token-efficiency Try it at Repo link below 👇

Jason Zhou

292,376 次观看 • 12 天前

introducing rumik oss 1 india's first state of the art open source, fully pre-trained voice model capable of speaking 20+ languages trained on only 66k hours of data, it beats even the top closed models on multiple benchmarks including emotion realism weights are now live 👇🏻

introducing rumik oss 1 india's first state of the art open source, fully pre-trained voice model capable of speaking 20+ languages trained on only 66k hours of data, it beats even the top closed models on multiple benchmarks including emotion realism weights are now live 👇🏻

rohan

104,936 次观看 • 1 个月前

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,227,092 次观看 • 2 个月前

Introducing Devin Security Swarm A more cost effective and accurate way to find security vulnerabilities in complex codebases, based on a new architecture: Agentic MapReduce.

Introducing Devin Security Swarm A more cost effective and accurate way to find security vulnerabilities in complex codebases, based on a new architecture: Agentic MapReduce.

Cognition

689,212 次观看 • 3 个月前

$Introducing Gemini 3 Flash! ⚡️⚡️⚡️ Frontier intelligence built for speed at a fraction of the cost. Here's ~4 minutes of demos.$

Introducing Gemini 3 Flash! ⚡️⚡️⚡️ Frontier intelligence built for speed at a fraction of the cost. Here's ~4 minutes of demos.

Addy Osmani

16,613 次观看 • 10 个月前

Today we are releasing two new benchmarks: MicroPlanBench (next-action prediction): GPT-6 Astra and GPT-6.1 Sol lead. Sol costs 1/5 as much. MicroAnnotationBench (labels + timing on long real-world clips): our nanoannot-1 beats Gemini 4 Argon, at 1/10 the cost.

Today we are releasing two new benchmarks: MicroPlanBench (next-action prediction): GPT-6 Astra and GPT-6.1 Sol lead. Sol costs 1/5 as much. MicroAnnotationBench (labels + timing on long real-world clips): our nanoannot-1 beats Gemini 4 Argon, at 1/10 the cost.

Bercan

463,508 次观看 • 9 天前

Introducing Offloop! We're a team of four. Today our multi-agent harness hit state of the art on GDPval, ahead of Claude code and Codex across jobs that pay $2.4 trillion a year in the US. Offloop gives every knowledge worker what the Fortune 500 spends billions on: a high-performing agent army that runs itself and grows the business.

Introducing Offloop! We're a team of four. Today our multi-agent harness hit state of the art on GDPval, ahead of Claude code and Codex across jobs that pay $2.4 trillion a year in the US. Offloop gives every knowledge worker what the Fortune 500 spends billions on: a high-performing agent army that runs itself and grows the business.

Offloop

2,643,654 次观看 • 3 个月前

By popular demand, Hy3 from Tencent Hy is free in Nous Portal for an extra week! It is focused on cost-effective agentic use, and is particularly strong on coding, tool-calling reliability, reasoning, and long-context tasks. Try Portal today at

By popular demand, Hy3 from Tencent Hy is free in Nous Portal for an extra week! It is focused on cost-effective agentic use, and is particularly strong on coding, tool-calling reliability, reasoning, and long-context tasks. Try Portal today at

Nous Research

123,969 次观看 • 3 个月前

The IDE era is dead. Introducing Reason, the AI Teammate for work and code We made Reason manage customers, build itself and also make this video. Pareto-frontier on Terminal Bench 4.0 and DeepSWE Now you can try it for free ->

The IDE era is dead. Introducing Reason, the AI Teammate for work and code We made Reason manage customers, build itself and also make this video. Pareto-frontier on Terminal Bench 4.0 and DeepSWE Now you can try it for free ->

Reason

33,470 次观看 • 2 天前

OpenHands crushed Codex by 2.3× on token efficiency! We gave both agents the same task on the same model (Qwen3.5 35B): build an 8-bit Space Invaders in 3 iterations (build, fix, polish). Output: • OpenHands: 219K tokens, • Codex: 513K tokens, OpenHands beats Codex in local running. The difference is in how they handle context. OpenHands reuses the unchanged data across every pass and only pays for new tokens, while Codex re-sends and re-counts it every iteration. OpenHands finished a bit slower, but on local runs, tokens spent are the real cost.

OpenHands crushed Codex by 2.3× on token efficiency! We gave both agents the same task on the same model (Qwen3.5 35B): build an 8-bit Space Invaders in 3 iterations (build, fix, polish). Output: • OpenHands: 219K tokens, • Codex: 513K tokens, OpenHands beats Codex in local running. The difference is in how they handle context. OpenHands reuses the unchanged data across every pass and only pays for new tokens, while Codex re-sends and re-counts it every iteration. OpenHands finished a bit slower, but on local runs, tokens spent are the real cost.

atomic.chat

29,842 次观看 • 3 个月前