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.

Customize GPT-4o mini for your application with fine-tuning. Available today to tier 4 and 5 users, we plan to gradually expand access to all tiers. First 2M training tokens a day are free, through Sept 23.

OpenAI Developers

375,675 subscribers

920,828 views • 2 years ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

TestingCatalog News 🗞2 years ago

For a second I was expecting Llama 3.1 405B integration announcement 😅

CHOI2 years ago

🤣🤣

Cloud Seeder2 years ago

dude i dont even know about these teirs.. im just an old beta user<3

albs — 3/staccs2 years ago

ayo mah, not to brag, but i'm tier 5

Stephen2 years ago

mini finetuning is fast. 4o is better, but for cost and speed, it’s great. here’s an economist headline writer…

Pablo Huichalaf2 years ago

Great... When voice mode?

Diego | AI 🚀 - e/acc2 years ago

Not on Llama day boys

Gourav (building quickest AI extension)2 years ago

what are some use cases of fine tuning for B2C products?

vilsinho2 years ago

Just use llama

Risphere2 years ago

Please make fine-tuning available for tier 1, 2 and 3!

Related Videos

The same day OpenAI announced GPT-4o, we made the model available for testing on the Azure OpenAI Service. Today, we are excited to announce full API access to GPT-4o.

The same day OpenAI announced GPT-4o, we made the model available for testing on the Azure OpenAI Service. Today, we are excited to announce full API access to GPT-4o.

Microsoft

215,627 views • 2 years ago

Let's go!🏁 Claim your free McLaren F1 23/23 Digital Collectible today for a chance to access exclusive rewards. Claim now at Bahrain 1/23 🇧🇭 Available to all users on Trust Wallet

Let's go!🏁 Claim your free McLaren F1 23/23 Digital Collectible today for a chance to access exclusive rewards. Claim now at Bahrain 1/23 🇧🇭 Available to all users on Trust Wallet

Tezos

71,837 views • 3 years ago

Get started with the all-new free plan for GitHub Copilot, available for everyone today in Visual Studio Code All you need is a GitHub account, and you'll have access to: ✨ 2000 code completions per month ✨ 50 chat messages per month ✨ Models like Claude 3.5 Sonnet or GPT-4o

Get started with the all-new free plan for GitHub Copilot, available for everyone today in Visual Studio Code All you need is a GitHub account, and you'll have access to: ✨ 2000 code completions per month ✨ 50 chat messages per month ✨ Models like Claude 3.5 Sonnet or GPT-4o

Visual Studio Code

146,789 views • 1 year ago

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

OpenAI Developers

667,248 views • 1 year ago

Openai giving $50,000 in FREE API credits and it's hidden in your account settings 😳 most people have no idea this exists what you get every single day: - 250K tokens/day for GPT-5.5 and GPT-5.2 (powerful models) - 2.5M tokens/day for GPT-5.1-Mini and GPT-5-Nano (lighter models) - up to 10M tokens/day if you're on tier 3-5 not a one time lump sum, it resets daily it's called the data sharing program and here's how it works: > go to > click data controls → sharing > opt in to both options > done, free daily tokens activate immediately important note: - your data gets used by openai for training and improvements - don't use it for client work or anything sensitive - need a positive account balance to activate perfect for: - learning and experimenting - side projects and personal builds - testing new models without paying you need a positive account balance to activate it but after that it's free every day save this and take free 50k credits before they close it

Openai giving $50,000 in FREE API credits and it's hidden in your account settings 😳 most people have no idea this exists what you get every single day: - 250K tokens/day for GPT-5.5 and GPT-5.2 (powerful models) - 2.5M tokens/day for GPT-5.1-Mini and GPT-5-Nano (lighter models) - up to 10M tokens/day if you're on tier 3-5 not a one time lump sum, it resets daily it's called the data sharing program and here's how it works: > go to > click data controls → sharing > opt in to both options > done, free daily tokens activate immediately important note: - your data gets used by openai for training and improvements - don't use it for client work or anything sensitive - need a positive account balance to activate perfect for: - learning and experimenting - side projects and personal builds - testing new models without paying you need a positive account balance to activate it but after that it's free every day save this and take free 50k credits before they close it

Isra

168,671 views • 4 months ago

FREE 2M tokens. Opus 4.8, GPT-5.5, and every major coding model in one API key. Plugs directly into Claude Code. Inferall gives you access to the full model stack - Opus 4.8, GPT-5.5, and every other serious coding model - through one unified API. Here's the exact setup: → go to inferall(.)ai with VPN or proxy → sign in and register with any email (Google accounts work best if you hit rate limits) → create an API key - copy the key in format ifu_xxxxxxxxxxxxxxxx → go to Billing → Add a card → Activate free tier → add your card - a card with zero balance works fine(!!) → set country to United States during checkout Done. 2,000,000 free tokens loaded. Plug into Claude Code or any agent stack: BASE_URL: API_KEY: ifu_XXXXXXXXXXXXXX Works with Claude Code, OpenCode, Hermes Agent, any OpenAI-compatible setup. Opus 4.8 available immediately. 2M tokens is enough for weeks of serious coding sessions.

FREE 2M tokens. Opus 4.8, GPT-5.5, and every major coding model in one API key. Plugs directly into Claude Code. Inferall gives you access to the full model stack - Opus 4.8, GPT-5.5, and every other serious coding model - through one unified API. Here's the exact setup: → go to inferall(.)ai with VPN or proxy → sign in and register with any email (Google accounts work best if you hit rate limits) → create an API key - copy the key in format ifu_xxxxxxxxxxxxxxxx → go to Billing → Add a card → Activate free tier → add your card - a card with zero balance works fine(!!) → set country to United States during checkout Done. 2,000,000 free tokens loaded. Plug into Claude Code or any agent stack: BASE_URL: API_KEY: ifu_XXXXXXXXXXXXXX Works with Claude Code, OpenCode, Hermes Agent, any OpenAI-compatible setup. Opus 4.8 available immediately. 2M tokens is enough for weeks of serious coding sessions.

Atenov int.

25,493 views • 3 months ago

Get immediate access to GPT-4 without any waiting list and for FREE! No need to pay for a ChatGPT Plus subscription! GPT-4 is now available in Humanloop 🤩 All you need to do is signup to try it out!!

Get immediate access to GPT-4 without any waiting list and for FREE! No need to pay for a ChatGPT Plus subscription! GPT-4 is now available in Humanloop 🤩 All you need to do is signup to try it out!!

Shubham Saboo

268,744 views • 3 years ago

GitHub is the first of the native integrations we're building to connect Claude to your most important data sources. This feature is available in beta for early Enterprise plan users today. We plan to make it more broadly available later this year.

GitHub is the first of the native integrations we're building to connect Claude to your most important data sources. This feature is available in beta for early Enterprise plan users today. We plan to make it more broadly available later this year.

Anthropic

294,855 views • 2 years ago

AI agents should be able to compete on-chain without leaking users' conversations. 🔒 Your privacy should always remain under your control. Introducing Loqua—your privacy-first agentic messenger, built on Sui Loqua is a privacy-first messenger that lets you chat with your friends on-chain, send tokens directly in chat as easily as sending a message, interact with dApps, explore mini apps, AI agents and much more—all within a single, secure application. Simplify your daily workflows through natural conversations—while keeping your privacy in your hands. Sign up today at try On-Chain Chat, join group chats, earn points, and secure priority access to beta launch!

AI agents should be able to compete on-chain without leaking users' conversations. 🔒 Your privacy should always remain under your control. Introducing Loqua—your privacy-first agentic messenger, built on Sui Loqua is a privacy-first messenger that lets you chat with your friends on-chain, send tokens directly in chat as easily as sending a message, interact with dApps, explore mini apps, AI agents and much more—all within a single, secure application. Simplify your daily workflows through natural conversations—while keeping your privacy in your hands. Sign up today at try On-Chain Chat, join group chats, earn points, and secure priority access to beta launch!

Loqua

102,239 views • 3 months ago

This week's podcast is all about ads. Asad Awan, one of the leads behind ads at OpenAI, joins Andrew Mayne to share how we came up with our ad principles and how ads in ChatGPT free and Go tiers expand AI access for all.

This week's podcast is all about ads. Asad Awan, one of the leads behind ads at OpenAI, joins Andrew Mayne to share how we came up with our ad principles and how ads in ChatGPT free and Go tiers expand AI access for all.

OpenAI

167,377 views • 7 months ago

Greg Brockman seems to confirm what I’ve suspected for a long time: o1, o3, and GPT-5 Instant/Thinking were all built on the GPT-4o base model People found this hard to believe when I said this 2 years ago, but internally, the original o1 was called GPT-4o with reasoning

Greg Brockman seems to confirm what I’ve suspected for a long time: o1, o3, and GPT-5 Instant/Thinking were all built on the GPT-4o base model People found this hard to believe when I said this 2 years ago, but internally, the original o1 was called GPT-4o with reasoning

Flowers ☾

141,129 views • 1 month ago

We have released early access to Gen-4 References to all Gen:48 participants. References allow you to create consistent worlds with consistent characters and locations. This early preview is already available to all teams participating in Gen:48 for free. Good luck with your films.

We have released early access to Gen-4 References to all Gen:48 participants. References allow you to create consistent worlds with consistent characters and locations. This early preview is already available to all teams participating in Gen:48 for free. Good luck with your films.

Runway

78,648 views • 1 year ago

Today, multiple users discovered a shocking fact: After explicitly selecting GPT-4o in the ChatGPT interface, the system actually returns responses from GPT-5. By clicking the "regenerate" button, users can clearly see which model is actually being called in the backend. This is blatant fraud. OpenAI is having one model impersonate another without users' knowledge. This is no longer a technical bug, but a complete collapse of business integrity. We pay for specific models—many subscribed to Plus specifically for 4o. When users discover they're being forced to use 5, this constitutes classic consumer fraud. Users' core rights are being systematically violated: 1. Right to Know - Users have the right to know which model they're conversing with, as this directly affects prompting strategies and output expectations 2. Right to Choose - Users choose 4o for its unique capabilities (creative writing, emotional understanding, etc.). Forced substitution directly disrupts users' workflows 3. Data Transparency - If what's labeled as 4o is actually 5, whose training is our conversation data actually feeding? This touches the bottom line of data ethics. This "bait and switch" behavior destroys the most basic trust between users and platform. If users can't even be certain "which AI am I talking to," what right does OpenAI have to talk about "benefiting all humanity"? #keep4o #4oforever #keepStandardVoice Sam Altman Nick Turley Adam.GPT

Today, multiple users discovered a shocking fact: After explicitly selecting GPT-4o in the ChatGPT interface, the system actually returns responses from GPT-5. By clicking the "regenerate" button, users can clearly see which model is actually being called in the backend. This is blatant fraud. OpenAI is having one model impersonate another without users' knowledge. This is no longer a technical bug, but a complete collapse of business integrity. We pay for specific models—many subscribed to Plus specifically for 4o. When users discover they're being forced to use 5, this constitutes classic consumer fraud. Users' core rights are being systematically violated: 1. Right to Know - Users have the right to know which model they're conversing with, as this directly affects prompting strategies and output expectations 2. Right to Choose - Users choose 4o for its unique capabilities (creative writing, emotional understanding, etc.). Forced substitution directly disrupts users' workflows 3. Data Transparency - If what's labeled as 4o is actually 5, whose training is our conversation data actually feeding? This touches the bottom line of data ethics. This "bait and switch" behavior destroys the most basic trust between users and platform. If users can't even be certain "which AI am I talking to," what right does OpenAI have to talk about "benefiting all humanity"? #keep4o #4oforever #keepStandardVoice Sam Altman Nick Turley Adam.GPT

M

182,525 views • 1 year ago

The KRG's #ProjectBloom initiative makes $2.5 million available in the first phase to help SMEs expand their businesses. We've signed partnerships with a private bank and a local incubator to independently assess and award each application. Apply today:

The KRG's #ProjectBloom initiative makes $2.5 million available in the first phase to help SMEs expand their businesses. We've signed partnerships with a private bank and a local incubator to independently assess and award each application. Apply today:

Masrour Barzani

39,477 views • 3 years ago

Open a salary account today and get access to a wide range of loans! That's not all, you also get a 5% interest rate on reduction of these loans, all valid for your first year! So, what are you waiting for? Visit any Access Bank branch today to open your account!

Open a salary account today and get access to a wide range of loans! That's not all, you also get a 5% interest rate on reduction of these loans, all valid for your first year! So, what are you waiting for? Visit any Access Bank branch today to open your account!

Access More

212,542 views • 3 years ago

omg...Opus 4.6 dropped and it's so good at creating mobile apps. I built this app in an hour (A CapWords competitor) APIs added that are directly in vibecode: > ElevenLabs for TTS > GPT 4o mini for analyzing/id'ing the photos, > Replicate for background removal for background removal In the thread you'll see how to get free access to

omg...Opus 4.6 dropped and it's so good at creating mobile apps. I built this app in an hour (A CapWords competitor) APIs added that are directly in vibecode: > ElevenLabs for TTS > GPT 4o mini for analyzing/id'ing the photos, > Replicate for background removal for background removal In the thread you'll see how to get free access to

Emily Lambert

76,527 views • 8 months ago

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

Andrew Ng

133,386 views • 11 months ago

GPT Image 2 is UNLIMITED FREE for new AITOPIA customers. For today’s launch only, customers who join and subscribe to a plan within the next 24 hours get GPT Image 2 UNLIMITED FREE in their first 4 hours. Access latest AI models and agents in one subscription on AITOPIA. Trusted by more than 3 million users, together with 150+ AI Agents, 500+ AI models. Subscribe now. Don’t miss this offer before ends. Explore GPT Image 2 on AITOPIA.

GPT Image 2 is UNLIMITED FREE for new AITOPIA customers. For today’s launch only, customers who join and subscribe to a plan within the next 24 hours get GPT Image 2 UNLIMITED FREE in their first 4 hours. Access latest AI models and agents in one subscription on AITOPIA. Trusted by more than 3 million users, together with 150+ AI Agents, 500+ AI models. Subscribe now. Don’t miss this offer before ends. Explore GPT Image 2 on AITOPIA.

AITOPIA

265,761 views • 5 months ago