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.

$200 to $20. That's how your AI costs will change if you switch from Claude Code Max to the MiniMax (official) Token Plan Plus in Kilo. MiniMax's latest model, M3, performs at 79% of Sonnet 5's level for a tenth of the price, and the plan gets you 1.7B... show more

Kilo

28,043 subscribers

25,441 views • 9 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

PEOPLE ARE BURNING THROUGH THEIR TOKENS IN 30 MINUTES AND BLAMING CLAUDE The problem isn’t with the model. The problem is how they’re using it A simple formatting question they set Max effort The 40th message in the chat the model re-reads the entire history from the beginning Every single time. Using your tokens Low effort costs 10 times less than Max Just get into the habit of routing tasks by level and your limit won’t run out by noon Tokens don’t disappear. You’re just paying for unnecessary processing

PEOPLE ARE BURNING THROUGH THEIR TOKENS IN 30 MINUTES AND BLAMING CLAUDE The problem isn’t with the model. The problem is how they’re using it A simple formatting question they set Max effort The 40th message in the chat the model re-reads the entire history from the beginning Every single time. Using your tokens Low effort costs 10 times less than Max Just get into the habit of routing tasks by level and your limit won’t run out by noon Tokens don’t disappear. You’re just paying for unnecessary processing

Asteri

15,752 views • 1 month ago

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇

EyeingAI

40,959 views • 4 months ago

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

Axel Bitblaze 🪓

47,438 views • 19 days ago

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

Sean Strong

115,687 views • 9 months ago

PAYING PER MODEL IS THE DUMBEST THING IN TECH RIGHT NOW i was paying 3x what i needed to for AI inference the grid lets you buy a quality spec instead of a specific model.. it routes every request in real time to the cheapest option that qualifies swap one url and your code keeps working exactly the same openai-compatible, one line to switch, 200M free tokens to start

PAYING PER MODEL IS THE DUMBEST THING IN TECH RIGHT NOW i was paying 3x what i needed to for AI inference the grid lets you buy a quality spec instead of a specific model.. it routes every request in real time to the cheapest option that qualifies swap one url and your code keeps working exactly the same openai-compatible, one line to switch, 200M free tokens to start

Robin Delta

15,729 views • 1 month ago

AIOZ AI Playgrounds are LIVE. Now it’s time to explore! Introducing AIOZ AI Model of the Month, a new campaign highlighting one featured model and rewarding your creativity. How to join: → Explore the featured model in its dedicated AIOZ AI Playground → Post your Playground results on X with a screenshot including input & output → Reply to this post with your screenshot to enter the lucky draw Lucky draw rewards: → 5 winners share 3,000 AIOZ tokens → AIOZ AI credits (credited directly on AIOZ AI) Duration: 1 month February Featured Model: Image to Anime Explore your first AI Playground and show us what you’ve created!

AIOZ AI Playgrounds are LIVE. Now it’s time to explore! Introducing AIOZ AI Model of the Month, a new campaign highlighting one featured model and rewarding your creativity. How to join: → Explore the featured model in its dedicated AIOZ AI Playground → Post your Playground results on X with a screenshot including input & output → Reply to this post with your screenshot to enter the lucky draw Lucky draw rewards: → 5 winners share 3,000 AIOZ tokens → AIOZ AI credits (credited directly on AIOZ AI) Duration: 1 month February Featured Model: Image to Anime Explore your first AI Playground and show us what you’ve created!

AIOZ Network

755,139 views • 4 months ago

🚨 FREE AI CODING MODEL ALERT! Tencent Hy's latest model, HY3, is now FREE in Kilo Code for a limited time. Here are the one-shot results when we prompted Opus, Fable, and HY3 to "Create a 3D HTML visualizer of Earth spinning in space" in Kilo's Agent Manager:

🚨 FREE AI CODING MODEL ALERT! Tencent Hy's latest model, HY3, is now FREE in Kilo Code for a limited time. Here are the one-shot results when we prompted Opus, Fable, and HY3 to "Create a 3D HTML visualizer of Earth spinning in space" in Kilo's Agent Manager:

Kilo

79,184 views • 10 days ago

I'm extremely hurt and uncomfortable with how so much of your original model was reused without permission. You seem to want to respect Lilly Lilly ✨🫠✨ and emphasize on how much the original model matters to you in the post, but you didn't even credit her once.

I'm extremely hurt and uncomfortable with how so much of your original model was reused without permission. You seem to want to respect Lilly Lilly ✨🫠✨ and emphasize on how much the original model matters to you in the post, but you didn't even credit her once.

Ponca 🦝 ENVtuber

45,179 views • 1 year ago

i've been paying 200$/month for AI tools for a while now claude, chatgpt, all of it thought that was just the price of doing things properly then i read this and had to close my laptop for a second someone bought a used GPU from eBay for $700 five years old. RTX 3090. the kind of card people sell when they upgrade for gaming plugged in a free model called Qwen 3.6 that alibaba quietly dropped last month and it scored 84.1 on vision tasks claude 4.5 opus scored 77.0 the 200$/month subscription lost to a free model running on old hardware the math gets worse after 4 months you've paid off the GPU from month 5 onwards you pay $8 for electricity that's it no subscription. no per message cost. nothing leaves your computer. ever. turns out i didn't have to is anyone else just finding out about this or was i the last one to know?

i've been paying 200$/month for AI tools for a while now claude, chatgpt, all of it thought that was just the price of doing things properly then i read this and had to close my laptop for a second someone bought a used GPU from eBay for $700 five years old. RTX 3090. the kind of card people sell when they upgrade for gaming plugged in a free model called Qwen 3.6 that alibaba quietly dropped last month and it scored 84.1 on vision tasks claude 4.5 opus scored 77.0 the 200$/month subscription lost to a free model running on old hardware the math gets worse after 4 months you've paid off the GPU from month 5 onwards you pay $8 for electricity that's it no subscription. no per message cost. nothing leaves your computer. ever. turns out i didn't have to is anyone else just finding out about this or was i the last one to know?

Crypto Mavka

14,126 views • 27 days ago

He earned $11,833 while his costs were the price of a McDonald's lunch Costs: > $9 > Claude API: $5 > InVideo: $20 Income: > $200+ per week > 10 channels = $2,000+ per week Claude writes the script. triggers the process. InVideo creates the 4K render. YouTube hosts the traffic. All that's left for you to do is hit the "Publish" button > Generates viral scripts, editing, voiceover, ideas, and descriptions -> a finished product 100% automation. Zero hassle

He earned $11,833 while his costs were the price of a McDonald's lunch Costs: > $9 > Claude API: $5 > InVideo: $20 Income: > $200+ per week > 10 channels = $2,000+ per week Claude writes the script. triggers the process. InVideo creates the 4K render. YouTube hosts the traffic. All that's left for you to do is hit the "Publish" button > Generates viral scripts, editing, voiceover, ideas, and descriptions -> a finished product 100% automation. Zero hassle

Bober_smart

28,398 views • 2 months ago

Holly shit❗️ Mark Carney thinks our effective carbon price is too low; "The effective carbon price in this country is actually quite low relative to the headline price,in the $20 to $30 range in most Canadian markets. And that's something we're working to rectify." The industrial carbon tax price increased to $110 this year, with a plan to increase it to a minimum of $130 and all the way to $170 around 2030. Do you understand how MASSIVE the increase to these levels will be to cost of things in Canada and how uncompetitive our industries will be!?

Holly shit❗️ Mark Carney thinks our effective carbon price is too low; "The effective carbon price in this country is actually quite low relative to the headline price,in the $20 to $30 range in most Canadian markets. And that's something we're working to rectify." The industrial carbon tax price increased to $110 this year, with a plan to increase it to a minimum of $130 and all the way to $170 around 2030. Do you understand how MASSIVE the increase to these levels will be to cost of things in Canada and how uncompetitive our industries will be!?

Kirk Lubimov

81,907 views • 2 months ago

Claude Code 2.1.90 just dropped with a new /powerup command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!

Claude Code 2.1.90 just dropped with a new /powerup command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!

Daniel San

271,237 views • 3 months ago

A trio of mathematicians built the first physical model of a “monostable” tetrahedron, a shape that will always flip-flop onto the same face no matter what side you place it on. In order for it to work properly, it had to be engineered to a level of precision within one-tenth of a gram and one-tenth of a millimeter. (From the archive)

A trio of mathematicians built the first physical model of a “monostable” tetrahedron, a shape that will always flip-flop onto the same face no matter what side you place it on. In order for it to work properly, it had to be engineered to a level of precision within one-tenth of a gram and one-tenth of a millimeter. (From the archive)

Quanta Magazine

64,668 views • 4 months ago

KIMI K2.6 SERVERS BURN 30 MILLION LITERS OF WATER A MONTH. INDIE DEVS USE THE SAME MODEL FOR $30 IN TOKENS TO LAUNCH $20,000/MONTH APPS IN A WEEKEND kimi k2.6 sits at number 1 on the openrouter leaderboard processing 1.58 trillion tokens a week. more than claude sonnet 4.6 and deepseek combined indie developers who launched in 2024-2025 are making $10,000-20,000 a month solo. no team, no office, $20 in starting costs. most aren't even senior devs the stack is next.js, supabase, stripe and kimi k2.6. you give the model 5 open source repos as reference and it assembles the product from the best parts of each 3,000 paying users at $9.99 a month is $29,970 in revenue. infrastructure costs $1,235. net profit lands at $28,735 with a 95% margin most people will bookmark this and forget. the ones who ship this weekend get a 6-12 month head start in app store rankings over everyone who starts later bookmark this and read the article below

KIMI K2.6 SERVERS BURN 30 MILLION LITERS OF WATER A MONTH. INDIE DEVS USE THE SAME MODEL FOR $30 IN TOKENS TO LAUNCH $20,000/MONTH APPS IN A WEEKEND kimi k2.6 sits at number 1 on the openrouter leaderboard processing 1.58 trillion tokens a week. more than claude sonnet 4.6 and deepseek combined indie developers who launched in 2024-2025 are making $10,000-20,000 a month solo. no team, no office, $20 in starting costs. most aren't even senior devs the stack is next.js, supabase, stripe and kimi k2.6. you give the model 5 open source repos as reference and it assembles the product from the best parts of each 3,000 paying users at $9.99 a month is $29,970 in revenue. infrastructure costs $1,235. net profit lands at $28,735 with a 95% margin most people will bookmark this and forget. the ones who ship this weekend get a 6-12 month head start in app store rankings over everyone who starts later bookmark this and read the article below

starmex

31,826 views • 1 month ago

Code LLaMA is now on Perplexity’s LLaMa Chat! Try asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!

Code LLaMA is now on Perplexity’s LLaMa Chat! Try asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!

Perplexity

274,570 views • 2 years ago

this is f**king dangerous someone figured out how to make Opus 4.8 run on Fable 5's brain with one prompt access to the best model is never guaranteed. It disappeared once already this year. but you can use it forever. here's how: 1. ask Fable 5: "write the operating manual your replacement will run on" (procedures, failure modes, a 5-question self-test) 2. save the output as one .md file and drop it into a new Claude Project as the project instructions 3. switch to Opus 4.8 and now your everyday model runs off the smart one's method, no top-tier price save and bookmark this no matter what full extraction prompt is in the article below: ↓

this is f**king dangerous someone figured out how to make Opus 4.8 run on Fable 5's brain with one prompt access to the best model is never guaranteed. It disappeared once already this year. but you can use it forever. here's how: 1. ask Fable 5: "write the operating manual your replacement will run on" (procedures, failure modes, a 5-question self-test) 2. save the output as one .md file and drop it into a new Claude Project as the project instructions 3. switch to Opus 4.8 and now your everyday model runs off the smart one's method, no top-tier price save and bookmark this no matter what full extraction prompt is in the article below: ↓

Hamza Khalid

32,300 views • 7 days ago

Added context to my tiny diffusion model to enable sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a ___ ___”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.

Added context to my tiny diffusion model to enable sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a _ _”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.

Nathan Barry

89,040 views • 8 months ago

What happens next? We took a photo with Lens and asked Nano Banana to generate the next 5 seconds of a scene. While it’s not predicting the future in a literal sense, the model draws upon its vast world knowledge to generate a plausible outcome in each of these examples. It's a fun peek at how our latest AI image editing model can be used for creative forecasting and storytelling. Nano Banana is now live in Search – accessible through Lens and AI Mode – so you can try this out for yourself!

What happens next? We took a photo with Lens and asked Nano Banana to generate the next 5 seconds of a scene. While it’s not predicting the future in a literal sense, the model draws upon its vast world knowledge to generate a plausible outcome in each of these examples. It's a fun peek at how our latest AI image editing model can be used for creative forecasting and storytelling. Nano Banana is now live in Search – accessible through Lens and AI Mode – so you can try this out for yourself!

Rajan Patel

74,826 views • 9 months ago