Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We just solved all usage limits on Grok Bot. Introducing Unlimited Model Usage: when your own subscription runs out, Reason rolls over to our models and keeps going. On a harness 22% cheaper per solved task than Codex. Free trial at

Reason Machines (YC F26)

14,780 subscribers

75,024 views • 1 day ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

21 Comments

LiteEagle2621 day ago

I dont understand is reason supposed to be a competitor to grok bot/hermes or is it supposed to be a coding agent?

Reason Machines (YC F26)1 day ago

Both! A more cost effective agent!

shashank sn1 day ago

now this is a header i can understand. good job.

aloha1 day ago

Reason for the win 🫡🫡

vexor4i1 day ago

Solid move. Seamless failover is the feature nobody builds until they lose a deploy. Pricing under Codex makes the switch a no brainer. Link saved.

Reason Machines (YC F26)1 day ago

Dope!

Darkking.skr1 day ago

我不認為你的收費合理

Fushift1 day ago

I would switch if you had a android app

Fushift1 day ago

Oh hell yeah, do you have a good mobile app and connectors?

Reason Machines (YC F26)1 day ago

TestFlight live! All connectors in the world

Legendary1 day ago

iOS App coming?

Reason Machines (YC F26)1 day ago

Already live!

lucid1 day ago

unlimited usage?

Reason Machines (YC F26)1 day ago

Yes unlimited models!

Kabel-Salat | AI & Tech1 day ago

When it rolls over mid-task, does the session keep its full context on your model, or restart from a summary? That handoff is usually where an agent run falls apart.

Nathan Barker1 day ago

Wait unlimited ??

igli.eth1 day ago

My usage did not reset…

MB1 day ago

Post a video of this working please

Upserto1 day ago

I'd make the fallback model visible in the run history, along with any change in tool support. Seamless handoffs are lovely, but the new coworker should still wear a name tag.

Bin1 day ago

For which level usage? Super grok?

Reason Machines (YC F26)1 day ago

GLM 5.3 Flash and DeepSeek V4.1 Flash!

Related Videos

We made Grok bot with unlimited usage! Fully Open-Sourced! Meet MausBot Bring your own Claude , grok, gemini, Codex Subs, and code with a frontier agent that has no limits! Try it for free at

We made Grok bot with unlimited usage! Fully Open-Sourced! Meet MausBot Bring your own Claude , grok, gemini, Codex Subs, and code with a frontier agent that has no limits! Try it for free at

Aditya Umale

23,308 views • 8 days ago

We made Grokbot with unlimited usage! Meet Reason Bring your own Claude or Codex Subs, and code with a frontier agent that has no limits! Try it for free at

We made Grokbot with unlimited usage! Meet Reason Bring your own Claude or Codex Subs, and code with a frontier agent that has no limits! Try it for free at

Reason Machines (YC F26)

718,587 views • 9 days ago

we made an open-source Grok Bot with unlimited usage! meet MausBot use your existing subscriptions: Claude, Codex, or even local models. Try it here -

we made an open-source Grok Bot with unlimited usage! meet MausBot use your existing subscriptions: Claude, Codex, or even local models. Try it here -

Omkar Satpute

11,117 views • 8 days ago

Made more improvements to the usage view in T3 Code. Much easier to see where your "spend" is and how different models behave based on your own data btw this measures all usage of Claude Code and Codex on your machines, not just usage within T3 Code :)

Made more improvements to the usage view in T3 Code. Much easier to see where your "spend" is and how different models behave based on your own data btw this measures all usage of Claude Code and Codex on your machines, not just usage within T3 Code :)

Theo - t3.gg

43,472 views • 1 month ago

Our free plan just got a major upgrade. All free users now get 25 prompt credits for premium model usage, unlimited usage of Cascade Base (even in Write mode), unlimited fast Tab completions, and access to App Deploys. Also, we changed our logo!

Devin Desktop

122,455 views • 1 year ago

i love Grok Grok Bot i do not love its rate limits here is a simple way to get more usage out of it: install your coding agents on Grok Bot's virtual machine Codex, Cursor, Grok Build, Antigravity, etc then, install herdr to manage those CLI agent sessions now give Grok Bot a rule: use Herdr + CLI agents for anything more than conversational tasks your rate limits for Grok Bot will only be coordination and prompting, rather than the coding tasks themselves and you can use those Cursor and Grok Build limits AND crank on Grok Bot without getting rate limited as fast

i love Grok Grok Bot i do not love its rate limits here is a simple way to get more usage out of it: install your coding agents on Grok Bot's virtual machine Codex, Cursor, Grok Build, Antigravity, etc then, install herdr to manage those CLI agent sessions now give Grok Bot a rule: use Herdr + CLI agents for anything more than conversational tasks your rate limits for Grok Bot will only be coordination and prompting, rather than the coding tasks themselves and you can use those Cursor and Grok Build limits AND crank on Grok Bot without getting rate limited as fast

Aaron Makelky

193,728 views • 2 months ago

“We’ve solved the model, but we have not solved the data at all.” Shaw, creator of elizaOS, on why AI progress depends less on models – and more on scientific rigor and trusted data.

“We’ve solved the model, but we have not solved the data at all.” Shaw, creator of elizaOS, on why AI progress depends less on models – and more on scientific rigor and trusted data.

OriginTrail

15,426 views • 10 months ago

Introducing the ChatGPT & Codex Stream Deck plugin. Your AI workflow is now on keys and dials: 🚦 Monitor chat status 💬 Send prompts 🎙️ Dictate prompts 🧭 Steer Codex tasks mid-run 🎛️ Dial in model and reasoning effort 📊 Preview usage and limits Get it free on Marketplace:

Introducing the ChatGPT & Codex Stream Deck plugin. Your AI workflow is now on keys and dials: 🚦 Monitor chat status 💬 Send prompts 🎙️ Dictate prompts 🧭 Steer Codex tasks mid-run 🎛️ Dial in model and reasoning effort 📊 Preview usage and limits Get it free on Marketplace:

Elgato

34,384 views • 1 month ago

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Harsh Savergaonkar

26,500 views • 1 month ago

A 9B model from Satya Nadella's Microsoft just beat Sam Altman's GPT-6 Sol at a Rubik's Cube, and it's built on Alibaba's Qwen Same scramble, same 12-move solution for all 4 models, 1 model call per move, real time Results: Microsoft Decision-1: solved in 5.9s for $151 per 1M solves TypeSafe Jev: solved in 6.8s for the same $151 Alibaba Qwen3.8 27B: solved in 10.4s for $5,040, open weights OpenAI GPT-6 Sol: stuck on move 8 when the clip ends, $31,200 per 1M solves OpenAI's flagship burns 206x more money than Microsoft's 9B model to make the same moves, and a free-to-download Qwen running at $0.15 per million tokens still finishes 4x faster than GPT-6 Sol

A 9B model from Satya Nadella's Microsoft just beat Sam Altman's GPT-6 Sol at a Rubik's Cube, and it's built on Alibaba's Qwen Same scramble, same 12-move solution for all 4 models, 1 model call per move, real time Results: Microsoft Decision-1: solved in 5.9s for $151 per 1M solves TypeSafe Jev: solved in 6.8s for the same $151 Alibaba Qwen3.8 27B: solved in 10.4s for $5,040, open weights OpenAI GPT-6 Sol: stuck on move 8 when the clip ends, $31,200 per 1M solves OpenAI's flagship burns 206x more money than Microsoft's 9B model to make the same moves, and a free-to-download Qwen running at $0.15 per million tokens still finishes 4x faster than GPT-6 Sol

leopardracer

23,206 views • 1 month ago

Introducing Bolt Forge. Free until Oct 14th: - Up to 50x more usage - The new frontier: GLM, DeepSeek, Kimi - Zero usage charges Live now in your model picker on And one more thing... 👇

Introducing Bolt Forge. Free until Oct 14th: - Up to 50x more usage - The new frontier: GLM, DeepSeek, Kimi - Zero usage charges Live now in your model picker on And one more thing... 👇

bolt.new

2,236,910 views • 1 month ago

🚨UPDATED CODEX JUST GOT FREE ACCESS TO GPT-6 PRO AND GPT-5.6 PRO CODEX JUST GOT A SERIOUS UPGRADE Codex Web now lets you use your ChatGPT Web models directly inside Codex. < GPT-6 Pro < GPT-5.6 Pro < More Web models < Full harness support < Pro usage tracking in the launcher This basically brings the power of ChatGPT’s Pro models into your coding workflow without leaving Codex. And the launcher now shows your Pro usage, so you can actually keep track of how much you’re using while you build. Codex is becoming more than just a coding agent. It’s turning into a full workspace for running the best models directly against your codebase. Repo in replies.

🚨UPDATED CODEX JUST GOT FREE ACCESS TO GPT-6 PRO AND GPT-5.6 PRO CODEX JUST GOT A SERIOUS UPGRADE Codex Web now lets you use your ChatGPT Web models directly inside Codex. < GPT-6 Pro < GPT-5.6 Pro < More Web models < Full harness support < Pro usage tracking in the launcher This basically brings the power of ChatGPT’s Pro models into your coding workflow without leaving Codex. And the launcher now shows your Pro usage, so you can actually keep track of how much you’re using while you build. Codex is becoming more than just a coding agent. It’s turning into a full workspace for running the best models directly against your codebase. Repo in replies.

Melophile

195,792 views • 1 month ago

HOLY SH*T, JENSEN HUANG SAYS GROK BOT USAGE IS SKYROCKETING, AND ELON IS DOING SOMETHING ALMOST NOBODY ELSE DOES JENSEN HUANG SAYS GROK BOT USAGE IS SKYROCKETING, AND ELON IS DOING SOMETHING ALMOST NOBODY ELSE DOES nvidia's ceo, spent one minute on elon and grok bot. what he said: 1. elon trains and runs his own models on nvidia chips 2. grok bot demand is climbing fast, jensen called it super cool 3. elon also rents that compute out to other companies 4. building it, running it and renting it: the only other one jensen names is google 5. his take on elon: nobody knows more about energy start small: give grok bot one research task you keep putting off. save this and read the article below to make money with grok bot ↓

HOLY SH*T, JENSEN HUANG SAYS GROK BOT USAGE IS SKYROCKETING, AND ELON IS DOING SOMETHING ALMOST NOBODY ELSE DOES JENSEN HUANG SAYS GROK BOT USAGE IS SKYROCKETING, AND ELON IS DOING SOMETHING ALMOST NOBODY ELSE DOES nvidia's ceo, spent one minute on elon and grok bot. what he said: 1. elon trains and runs his own models on nvidia chips 2. grok bot demand is climbing fast, jensen called it super cool 3. elon also rents that compute out to other companies 4. building it, running it and renting it: the only other one jensen names is google 5. his take on elon: nobody knows more about energy start small: give grok bot one research task you keep putting off. save this and read the article below to make money with grok bot ↓

spect

2,234,440 views • 26 days ago

I burned a shitload of compute so you don't have to. Releasing the Harness Leaderboard. Which harness should you run your open model in? I ran 28,849 trials to find out. The leaderboard compares nine coding-agent harnesses on open models. In each comparison only the harness changes: the model, provider and reasoning effort stay fixed, and every task gets three attempts. The trials ran GLM-5.3-Flash, DeepSeek-V4.1-Flash and Flint on Terminal-Bench 2.1 and DeepSWE, for $4,746 of inference. Averaged over the three models, mini-swe-agent (Kilian Lieret), a bash-only agent, solves 51.4% of tasks and OpenClaw🦞 27.3%. Four others are statistically tied with mini-swe-agent. One of them is Pi (Pi), at 49.4% for $0.29 per solved task, about 45% less than mini-swe-agent's $0.53. The best harness depends on the model: mini-swe-agent on GLM-5.3-Flash, Hermes Agent (Nous Research) on DeepSeek-V4.1-Flash and Kimi Code (Kimi.ai) on Flint. OpenCode costs $3.35 per solved task, 11.7 times as much as Pi. See Harness Hub's Harness Lens for what the nine harnesses do differently. It documents the prompts, tools and compaction of 34 coding-agent harnesses and links every claim to its source. Leaderboard: Harness Lens:

I burned a shitload of compute so you don't have to. Releasing the Harness Leaderboard. Which harness should you run your open model in? I ran 28,849 trials to find out. The leaderboard compares nine coding-agent harnesses on open models. In each comparison only the harness changes: the model, provider and reasoning effort stay fixed, and every task gets three attempts. The trials ran GLM-5.3-Flash, DeepSeek-V4.1-Flash and Flint on Terminal-Bench 2.1 and DeepSWE, for $4,746 of inference. Averaged over the three models, mini-swe-agent (Kilian Lieret), a bash-only agent, solves 51.4% of tasks and OpenClaw🦞 27.3%. Four others are statistically tied with mini-swe-agent. One of them is Pi (Pi), at 49.4% for $0.29 per solved task, about 45% less than mini-swe-agent's $0.53. The best harness depends on the model: mini-swe-agent on GLM-5.3-Flash, Hermes Agent (Nous Research) on DeepSeek-V4.1-Flash and Kimi Code (Kimi.ai) on Flint. OpenCode costs $3.35 per solved task, 11.7 times as much as Pi. See Harness Hub's Harness Lens for what the nine harnesses do differently. It documents the prompts, tools and compaction of 34 coding-agent harnesses and links every claim to its source. Leaderboard: Harness Lens:

Joël Niklaus

325,487 views • 5 days ago

Introducing LiveKit Inference — a new cloud service that gives you access to the most popular voice AI models with just your LiveKit API key. We manage rate limits for you, report on usage, and consolidate billing. All LiveKit Cloud plans now include free monthly inference credits. A single string update allows you to call models from: AssemblyAI Deepgram Google DeepMind OpenAI Rime

Introducing LiveKit Inference — a new cloud service that gives you access to the most popular voice AI models with just your LiveKit API key. We manage rate limits for you, report on usage, and consolidate billing. All LiveKit Cloud plans now include free monthly inference credits. A single string update allows you to call models from: AssemblyAI Deepgram Google DeepMind OpenAI Rime

LiveKit

37,257 views • 1 year ago

SpaceXAI just showed how to use Grok Bot: 00:00 - build your first Grok Bot agent 12:22 - how to delegate task between Grok Bot agents 21:03 - Grok bot runs 24/7 51:12 - how to build Grok Bot team worth more than any paid course on Grok Bot agents Watch today, then read how to build a Grok bot agents team from scratch in article below

SpaceXAI just showed how to use Grok Bot: 00:00 - build your first Grok Bot agent 12:22 - how to delegate task between Grok Bot agents 21:03 - Grok bot runs 24/7 51:12 - how to build Grok Bot team worth more than any paid course on Grok Bot agents Watch today, then read how to build a Grok bot agents team from scratch in article below

0xRafy

54,975 views • 2 months ago

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

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

25,194 views • 28 days ago

Dynamic memory is now out in stable OrbStack v1.7.0! Memory usage is finally a solved problem

Dynamic memory is now out in stable OrbStack v1.7.0! Memory usage is finally a solved problem

OrbStack

34,664 views • 2 years ago

I updated Codex Web GPT. You can now use all your ChatGPT Web models (GPT-6 Pro, GPT-5.6 Pro...) directly inside Codex, with the full harness and their separate Web limits. The launcher now tracks Pro usage too, so you can keep an eye on it as you work. Repo in replies.

I updated Codex Web GPT. You can now use all your ChatGPT Web models (GPT-6 Pro, GPT-5.6 Pro...) directly inside Codex, with the full harness and their separate Web limits. The launcher now tracks Pro usage too, so you can keep an eye on it as you work. Repo in replies.

vechen

87,360 views • 1 month ago

The ultimate Grok Bot usage hack! HEAVY lift cloud agents skill. The problem statement was I had been consuming all my grok bot weekly usage & zippo of my monthly cursor ultra tokens. Well now that’s all changed! I created a skill with my chief of staff that is to use Cursor cloud agents for any heavy lifting (they have vm/web surfing too!) where my grok bots only act as management (not real work but still useful) Results are real, task that took 5% bot usage are now redistributed on my cursor monthly allotment and grok bot is now consuming sub 1% weekly usage for the same if not higher throughput, because I instructed the skill to long running grok 4.6 agents sized for the task at hand.

The ultimate Grok Bot usage hack! HEAVY lift cloud agents skill. The problem statement was I had been consuming all my grok bot weekly usage & zippo of my monthly cursor ultra tokens. Well now that’s all changed! I created a skill with my chief of staff that is to use Cursor cloud agents for any heavy lifting (they have vm/web surfing too!) where my grok bots only act as management (not real work but still useful) Results are real, task that took 5% bot usage are now redistributed on my cursor monthly allotment and grok bot is now consuming sub 1% weekly usage for the same if not higher throughput, because I instructed the skill to long running grok 4.6 agents sized for the task at hand.

Try TLGen App | Brandon Starship 🇺🇸

44,983 views • 2 months ago