Keeping track of all the new AI models getting released at the moment is practically a full-time job. The most recent model, GPT-5.4, was released literally days after GPT-5.3 (and was barely a release to begin with).
I've been writing about OpenAI's models for the past few years, and it feels like every time I publish an article, another new model drops. OpenAI is one of the worst offenders (or prolific innovators), and things aren't helped by how confusing all the OpenAI model names are.
So, let's try to simplify things: consider this your complete guide to all of OpenAI's major models. We'll look at what each one is good for, how much they cost, and how to make the most of them in your work.
But first, I have to apologize for the crimes against consistent naming conventions, capitalization, and hyphenation we're all going to have to endure. GPT-5 nano, gpt-oss-120b, and GPT Image 1.5 are a few of OpenAI's models. Hang in there.
Table of contents:
Why are there so many OpenAI models?
OpenAI is one of the most important AI companies. Its ChatGPT chatbot and DALL·E 2 image generator essentially kickstarted the current AI boom. Over the past few years, it's continued to develop large language models, multimodal models, and text-to-image models.
OpenAI is moving fast. As the technology advances, new models have come out, and we've naturally been left with an extensive list—including some legacy models.
Note: Some of the models below are accessible through ChatGPT, but we'll mostly be looking at the models available through OpenAI's API. That means you can also use them to develop your own AI-powered tools and connect them to thousands of other apps using Zapier.
OpenAI models at a glance
Model | Best for | Inputs | Outputs | Context window | Pricing (input / output per M tokens) | Notes |
|---|---|---|---|---|---|---|
GPT-5.4 | Advanced reasoning and logic | Text, Images | Text | 1 million tokens | $2.50 / $15 | Flagship reasoning model; best for coding, logic, scientific tasks; token cost is higher for long context tasks |
GPT-5.4 pro | Research | Text, Images | Text | 1 million tokens | $30 / $180 | Uses more compute for problems that need deeper reasoning |
GPT-5.2 | Superseded by GPT-5.4 | Text, Images | Text | 400,000 tokens | $1.75 / $14 | You should update any tools you've built with GPT-5.2 to GPT-5.4 |
GPT-5.2 pro | Superseded by GPT-5.4 pro | Text, Images | Text | 400,000 tokens | $21 / $168 | You should update any tools you've built with GPT-5.2 pro to GPT-5.4 pro |
GPT-5.1 | Superseded by GPT-5.2 | Text, Images | Text | 400,000 tokens | $1.25 / $10 | You should update any tools you've built with GPT-5.1 to GPT-5.4 |
GPT-5 | Superseded by GPT-5.2 | Text, Images | Text | 400,000 tokens | $1.25 / $10 | You should update any tools you've built with GPT-5 to GPT-5.4 |
GPT-5 mini | Affordable reasoning and logic | Text, Images | Text | 400,000 tokens | $0.25 / $2 | Faster and cheaper alternative to GPT-5; supports reasoning effort control |
GPT-5 nano | Very affordable reasoning and logic | Text, Images | Text | 400,000 tokens | $0.05 / $0.40 | Fastest, cheapest GPT-5 reasoning model; ideal for summaries and classification |
GPT-5.3 Codex | Advanced coding | Text, Images | Text | 400,000 tokens | $1.25 / $10 | Designed for code generation |
GPT-4.1 | Complex tasks without advanced reasoning | Text, Images | Text | 1,047,576 tokens | $2 / $8 | Versatile, powerful general model |
GPT-4.1 mini | Balance of power, performance, and affordability | Text, Images | Text | 1,047,576 tokens | $0.40 / $1.60 | Great general-purpose starting point |
GPT-4.1 nano | Speed and price optimization | Text, Images | Text | 1,047,576 tokens | $0.10 / $1.40 | Fastest and cheapest GPT-4.1 model |
gpt-audio-1.5 | Audio | Text, Audio | Text, Audio | 128,000 tokens | Text: $2.50 / $10; Audio: $32 / $64 | Has both audio in and audio out in API |
gpt-audio-mini | Audio on a budget | Text, Audio | Text, Audio | 128,000 tokens | Text: $0.60 / $2.40; Audio: $10 / $20 | Budget-friendly audio model |
gpt-oss-120b | Open weight model | Text | Text | 131,072 tokens | Varies by provider | 117B params; 5.1B active; Apache 2.0; downloadable, fine-tunable, single H100 capable |
gpt-oss-20b | Medium open weight model | Text | Text | 131,072 tokens | Varies by provider | 21B params; 3.6B active; Apache 2.0; laptop/local deployable open weight model |
GPT Image 1.5 | Image generation | Text, Images | Text, Images | N/A | Text: $5/10; Image: $10 / $32 | Successor to DALL·E; top-tier image generation |
GPT Image 1 | Image generation | Text, Images | Images | N/A | Text: $5; Image: $10 / $40 | Superseded by GPT Image 1 |
Sora 2 | Video generation | Text, Images, Videos | Videos | N/A | $0.10 – $0.50/second | Pro creates higher quality videos that take longer to render |
Sora | Video generation | Text, Images, Videos | Videos | N/A | $20/month (Plus); $200/month (Pro) | Video generation not available via API |
GPT-5.4
Best OpenAI model for advanced reasoning and logic
GPT-5.4 is OpenAI's flagship reasoning model and one of the most powerful AI models available right now. GPT-5.4 was released just a couple months after GPT-5.2 (and just days after GPT-5.3), but it was still a significant step up in benchmark performance. With every new model, Zapier tests on hundreds of real workflows, and GPT 5.4 was a top performer on messy, multi-step workflows where accuracy matters most.
Reasoning models like GPT-5.4 are best for logical, technical, and scientific tasks. If you need the most powerful model OpenAI has for building agentic tools, generating computer code, analyzing text documents and images, or solving complex puzzles, GPT-5.4 is the one to use. It's also the first general purpose model from OpenAI that has computer use abilities and has incorporated the previously standalone Codex model's coding capabilities.
Because reasoning models use additional resources to work through problems, they're more expensive for tasks that don't require advanced reasoning.
GPT-5.4 inputs: Text, images
GPT-5.4 outputs: Text
GPT-5.4 context window: 1 million tokens
GPT-5.4 input pricing: $2.50/M tokens (< 272k context); $5/M tokens
GPT-5.4 output pricing: $15/M tokens (<272k context); $22/M tokens
GPT-5.4 pro
Best OpenAI model for research and cutting edge uses
GPT-5.4 pro is a version of OpenAI's flagship reasoning model, GPT-5.4. It's designed to be the smartest and most trustworthy model for solving difficult problems where financial and time costs aren't significant barriers.
Responses from GPT-5.4 pro can take many times longer than other models, and it costs 12 times more to use GPT-5.4 pro than GPT-5.4. Unless you know you need its cutting edge performance, it's not the model to use.
GPT-5.4 pro inputs: Text, images
GPT-5.4 pro outputs: Text
GPT-5.4 pro context window: 1 million tokens
GPT-5.4 pro input pricing: $30/M tokens
GPT-5.4 pro output pricing: $180/M tokens
GPT-5.2
Superseded by GPT 5.4
GPT-5.2 was a huge step up for OpenAI when it was released in December 2025, but with GPT-5.4 coming on the scene just over two months later, it's already been superseded. It's still available in the API as a slightly more affordable option for the time being.
GPT-5.2 inputs: Text, images
GPT-5.2 outputs: Text
GPT-5.2 context window: 400,000 tokens
GPT-5.2 input pricing: $1.75/M tokens
GPT-5.2 output pricing: $14/M tokens
GPT-5.2 pro
Superseded by GPT-5.4 pro
GPT-5.2 pro is a version of OpenAI's GPT-5.2. It's been superseded by GPT-5.4 pro. It's still available in the API as a slightly more affordable option for the time being.
GPT-5.2 pro inputs: Text, images
GPT-5.2 pro outputs: Text
GPT-5.2 pro context window: 400,000 tokens
GPT-5.2 pro input pricing: $21/M tokens
GPT-5.2 pro output pricing: $168/M tokens
GPT-5.1 and GPT-5
Superseded by GPT-5.4
GPT-5.1 and GPT-5 are previous flagship models. Though they're still available through the API, you should update any tools you've built with them to GPT-5.4.
GPT-5.1/GPT-5 inputs: Text, images
GPT-5.1/GPT-5 outputs: Text
GPT-5.1/GPT-5 context window: 400,000 tokens
GPT-5.1/GPT-5 input pricing: $1.25/M tokens
GPT-5.1/GPT-5 output pricing: $10/M tokens
GPT-5 mini
Best OpenAI model for affordable reasoning and logic
GPT-5 mini is a faster and more affordable alternative to GPT-5. For well-defined or chatbot responses, it offers a great balance between power and performance.
Like GPT-5, you have to set a reasoning effort with GPT-5 mini. The lower the reasoning effort, the faster and more affordable it will be.
GPT-5 mini inputs: Text, images
GPT-5 mini outputs: Text
GPT-5 mini context window: 400,000 tokens
GPT-5 mini input pricing: $0.25/M tokens
GPT-5 mini output pricing: $2/M tokens
GPT-5 nano
Best OpenAI model for very affordable reasoning and logic
GPT-5 nano is OpenAI's fastest and most affordable reasoning model. It excels at tasks like summarization and classification. Like GPT-5 and GPT-5 mini, you have to set a reasoning effort with GPT-5 nano.
GPT-5 nano inputs: Text, images
GPT-5 nano outputs: Text
GPT-5 nano context window: 400,000 tokens
GPT-5 nano input pricing: $0.05/M tokens
GPT-5 nano output pricing: $0.40/M tokens
GPT-5.3 Codex
Superseded by GPT-5.4
GPT-5.3 Codex is a version of GPT-5 that's designed for agentic coding tasks in tools like Codex, Cursor, and Replit. It was best for complex and long-running coding tasks, like creating new functions and features and making major code base changes, but now, OpenAI recommends using GPT-5.4 for all of that.
The same is true of other versions of Codex, including GPT-5.2 Codex, GPT-5.1 Codex, GPT-5.1 Codex max, GPT-5.1 Codex mini, and GPT-5 Codex.
GPT-5.3 Codex inputs: Text, images
GPT-5.3 Codex outputs: Text
GPT-5.3 Codex context window: 400,000 tokens
GPT-5.3 Codex input pricing: $1.75/M tokens
GPT-5.3 Codex output pricing: $14/M tokens
GPT-4.1
Best OpenAI model for complex tasks that don't require advanced reasoning
GPT-4.1 is OpenAI's smartest non-reasoning multimodal LLM.
It's best to consider GPT-4.1 the ultimate Swiss Army knife of OpenAI's models. While there's very little it can't do, there are some situations where another model might be more appropriate. For example, a dedicated reasoning model will perform better on multi-step tasks like code generation, while a smaller cost-optimized model will offer better value for basic text generation.
GPT-4.1 inputs: Text, images
GPT-4.1 outputs: Text
GPT-4.1 context window: 1,047,576 tokens
GPT-4.1 input pricing: $2/M tokens
GPT-4.1 output pricing: $8/M tokens
GPT-4.1 mini
Best OpenAI model for balancing power, performance, and affordability
GPT-4.1 mini is a fast and affordable general-purpose AI model. In benchmarks, it performs almost as well as GPT-4.1 but at ⅕th the price. If you aren't sure which model to use, GPT-4.1 mini is probably the sensible starting point. Unless you know you need the extra power of GPT-4.1 or are concerned about cost optimization, it's a very strong option.
GPT-4.1 mini inputs: Text, images
GPT-4.1 mini outputs: Text
GPT-4.1 mini context window: 1,047,576 tokens
GPT-4.1 mini input pricing: $0.40/M tokens
GPT-4.1 mini output pricing: $1.60/M tokens
GPT-4.1 nano
Best OpenAI model for speed and price
GPT-4.1 nano is the smallest GPT-4.1 model available. As a result, it's the fastest and cheapest model—though it isn't as powerful as GPT-4.1 or GPT-4.1 mini. It's the model to use for simple tasks, or when you need to prioritize speed and cost-effectiveness.
GPT-4.1 nano inputs: Text, images
GPT-4.1 nano outputs: Text
GPT-4.1 nano context window: 1,047,576 tokens
GPT-4.1 nano input pricing: $0.10/M tokens
GPT-4.1 nano output pricing: $1.40/M tokens
gpt-audio-1.5
Best OpenAI model for audio
OpenAI's first generally available audio model, it supersedes GPT-Audio and the old GPT-4o Audio model. It can transcribe audio into text or reply with speech.
gpt-audio-1.5 inputs: Text, audio
gpt-audio-1.5 outputs: Text, audio
gpt-audio-1.5 context window: 128,000 tokens
gpt-audio-1.5 input pricing: $2.50/M tokens for text; $32/M tokens for audio
gpt-audio-1.5 output pricing: $10/M tokens for text; $64/M tokens for audio
gpt-audio-mini
Best OpenAI model for audio on a budget
GPT-Audio mini offers audio inputs and outputs for around a third of the cost of GPT Audio 1.5. For developers that need an audio model but are cost constrained, it's the best option.
gpt-audio-mini inputs: Text, audio
gpt-audio-mini outputs: Text, audio
gpt-audio-mini context window: 128,000 tokens
gpt-audio-mini input pricing: $0.60/M tokens for text; $10/M tokens for audio
gpt-audio-mini output pricing: $2.40/M tokens for text; $20/M tokens for audio
gpt-oss-120b
Best open weight OpenAI model
gpt-oss-120b is OpenAI's most powerful open weight model, and it's the most powerful open model that can run on a single H100 GPU. It's released under an Apache 2.0 license, so you can download it and run it on your own server or choose from any third-party inference provider. You can also fine-tune the model to suit your needs. This is big for OpenAI, which historically, has only released proprietary models.
gpt-oss-120b has 117 billion parameters. It uses a mixture-of-experts architecture, so only 5.1 billion parameters are active at once.
gpt-oss-120b inputs: Text
gpt-oss-120b outputs: Text
gpt-oss-120b context window: 131,072 tokens
gpt-oss-120b input pricing: Varies by provider
gpt-oss-120b output pricing: Varies by provider
gpt-oss-20b
Best medium open weight OpenAI model
gpt-oss-20b is OpenAI's medium open weight model. It's designed to run locally and can even run on a sufficiently powerful laptop. Like gpt-oss-120b, it's released under an Apache 2.0 license, so you can download it yourself or choose from any third-party inference provider, and you can fine-tune the model to suit your needs.
gpt-oss-20b has 21 billion parameters. It uses a mixture-of-experts architecture so only 3.6 billion parameters are active at once.
gpt-oss-120b inputs: Text
gpt-oss-120b outputs: Text
gpt-oss-120b context window: 131,072 tokens
gpt-oss-120b input pricing: Varies by provider
gpt-oss-120b output pricing: Varies by provider
GPT Image 1.5
Best OpenAI model for generating images
GPT Image 1.5 is the successor to OpenAI's DALL·E image models, and it's one of the best text-to-image models available. It supersedes GPT Image 1.
OpenAI's pricing for image models is quite complicated because images are converted into tokens based on their size and quality. However, it's not particularly expensive: it costs $0.10 to generate multiple 1024 x 1024 px high-quality images, for example.
GPT Image 1.5 inputs: Text, images
GPT Image 1.5 outputs: Images
GPT Image 1.5 input pricing: $5/M text tokens; $1/M image tokens
GPT Image 1.5 output pricing: $10/M text tokens; $32/M image tokens
GPT Image 1
Superseded by GPT Image 1.5
GPT Image 1 was the successor to OpenAI's DALL·E image models. It's now been superseded by GPT Image 1.5, though it's still available through the API.
GPT Image 1 inputs: Text, images
GPT Image 1 outputs: Images
GPT Image 1 input pricing: $5/M text tokens; $10/M image tokens
GPT Image 1 output pricing: $40/M image tokens
Sora 2
Best OpenAI model for generating video
Sora 2 is OpenAI's flagship video generation model. It can take a combination of text prompts, still images, and videos, and generate a video and audio clip based on all that. Sora 2 and Sora 2 Pro are available through the API. Sora 2 Pro creates higher quality and resolution video but takes longer to render.
Sora 2 inputs: Text, images, videos
Sora 2 outputs: Videos
Sora 2 pricing: $0.10/second for 720p video; Pro: $0.30/second for 720p video and $0.50/second for full HD video
Sora 1
Best OpenAI model for generating video through an app
Sora 1 powers OpenAI's Sora web app and mobile app. It isn't available as an API.
Free users can generate six watermarked 10-second videos in 720p resolution per day, while ChatGPT Plus subscribers have a higher usage limit. ChatGPT Pro subscribers can generate un-watermarked 20-second videos in 1080p resolution.
Sora inputs: Text, images, videos
Sora outputs: Videos
Sora pricing: Available free, as part of ChatGPT Plus ($20/month), and ChatGPT Pro ($200/month)
Legacy OpenAI models
OpenAI has developed and deprecated dozens of models over the past few years. Here are some of the major models that are no longer supported, actively used, or state-of-the-art:
o3
o3-pro
o4-mini
o1
o1-pro
GPT-4.5
GPT-4o
GPT-4o mini
GPT-4
GPT-3.5 Turbo
GPT-3
DALL·E 3
DALL·E 2
Whisper
How to choose the right OpenAI model
OpenAI has lots of models, but they each serve a purpose. GPT-5.4 and GPT-4.1 are the top reasoning and non-reasoning models, respectively, with the various mini and nano versions offering a different balance between price, performance, and speed. There's certainly a lot of overlap between the different models' abilities, especially when you take into account older models that haven't yet been replaced. But in general, one should strike you as the best balance between power, price, and ongoing development.
OpenAI keeps releasing new models, changing pricing, and otherwise mixing things up. I'll do my best to keep this list as current and accurate as possible in the meantime.
Automate OpenAI models
All the OpenAI models are the most helpful when they're part of your existing workflow. With Zapier's ChatGPT integration, you can use OpenAI's state-of-the-art models—including the recently released GPT-5.4—to automate everything from intelligent sales outreach to content generation to customer support. This means doing things like automatically identifying opportunities in your CRM, summarizing business information, and prioritizing your workflow—using all the apps already in your tech stack.
Learn more about how to automate OpenAI models with Zapier, or get started with one of these pre-made templates.
Automatically reply to Google Business Profile reviews with ChatGPT
Send prompts to ChatGPT for Google Forms responses and add the ChatGPT response to a Google Sheet
Create email copy with ChatGPT from new Gmail emails and save as drafts in Gmail
Create email copy with ChatGPT from new Microsoft Outlook emails and save as drafts
Zapier is the most connected AI orchestration platform—integrating with thousands of apps from partners like Google, Salesforce, and Microsoft. Use forms, data tables, and logic to build secure, automated, AI-powered systems for your business-critical workflows across your organization's technology stack. Learn more.
Related reading:
This article was originally published in May 2025. The most recent update was in March 2026.
