All the models and what they’re best for

Keeping track of all the new AI models getting released at the moment is practically a full-time job. The most recent model, GPT-5.6, was released less than three months after GPT 5.5, which itself was released two months after GPT-5.4.

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-5.6 Sol, GPT-5.4 nano, gpt-oss-120b, and GPT Image 2 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.

OpenAI models at a glance

Best OpenAI model for advanced reasoning and logic

GPT-5.6 Sol is the most advanced version of OpenAI’s flagship reasoning model, GPT-5.6, and it’s one of the most powerful AI models available right now. GPT-5.6 was released less than three months after GPT-5.5, but it was still a significant step up in benchmark performance. With every new model, Zapier tests on hundreds of real workflows, and GPT-5.6 Sol was a top performer on messy, multi-step workflows where accuracy matters most.

Reasoning models like GPT-5.6 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-5.6 Sol is the one to use. It also has computer use abilities and has incorporated the previously standalone Codex model’s coding capabilities.

It’s designed to be the smartest and most trustworthy model for solving difficult problems where financial and time costs aren’t significant barriers. It costs twice as much to use GPT-5.6 Sol compared to the Terra version of the model and five times more compared to the Luna version. Unless you know you need its cutting edge performance, it’s not the best model to start with.

• GPT-5.6 Sol inputs: Text, images

• GPT-5.6 Sol outputs: Text

• GPT-5.6 Sol context window: 1 million tokens

• GPT-5.6 Sol input pricing: $5/M tokens(< 272k context); $10/M tokens (> 272 context)

• GPT-5.6 Sol output pricing: $30/M tokens (< 272k context); $45/M tokens (> 272 context)

Best OpenAI model for balancing reasoning and cost

GPT-5.6 Terra is the middle-ground between the most powerful Sol model and the lighter weight and more affordable Luna model.

• GPT-5.6 Terra inputs: Text, images

• GPT-5.6 Terra outputs: Text

• GPT-5.6 Terra context window: 1 million tokens

• GPT-5.6 Terra input pricing: $2.50/M tokens(< 272k context); $5/M tokens (> 272 context)

• GPT-5.6 Terra output pricing: $15/M tokens (< 272k context); $22.50/M tokens (> 272 context)

Best OpenAI model for affordable reasoning and logic

GPT-5.6 Luna is a faster and more affordable alternative to GPT-5.6 Sol and Terra. For well-defined or chatbot responses, it offers a great balance between power and performance.

• GPT-5.6 Luna inputs: Text, images

• GPT-5.6 Luna outputs: Text

• GPT-5.6 Luna context window: 1 million tokens

• GPT-5.6 Luna input pricing: $1/M tokens(< 272k context); $2/M tokens (> 272 context)

• GPT-5.6 Luna output pricing: $6/M tokens (< 272k context); $9/M tokens (> 272 context)

Superseded

GPT-5.5 was OpenAI’s flagship reasoning model, but it’s been superseded by GPT-5.6.

• GPT-5.5 inputs: Text, images

• GPT-5.5 outputs: Text

• GPT-5.5 context window: 1 million tokens

• GPT-5.5 input pricing: $5/M tokens(< 272k context); $10/M tokens

• GPT-5.5 output pricing: $30/M tokens (< 272k context); $45/M tokens

Superseded

GPT-5.5 Pro was the most powerful version of OpenAI’s flagship reasoning model, but it’s been superseded by GPT-5.6 Sol.

• GPT-5.5 Pro inputs: Text, images

• GPT-5.5 Pro outputs: Text

• GPT-5.5 Pro context window: 1 million tokens

• GPT-5.5 Pro input pricing: $30/M tokens

• GPT-5.5 Pro output pricing: $180/M tokens

Superseded

GPT-5.4 mini was a faster and more affordable alternative to GPT-5.4 and GPT-5.5. It’s still slightly less expensive than GPT 5.6 Luna, but it’s been superseded by that model.

• GPT-5.4 mini inputs: Text, images

• GPT-5.4 mini outputs: Text

• GPT-5.4 mini context window: 400,000 tokens

• GPT-5.4 mini input pricing: $0.75/M tokens

• GPT-5.4 mini output pricing: $4.50/M tokens

Best OpenAI model for very affordable reasoning and logic

GPT-5.4 nano is OpenAI’s fastest and most affordable reasoning model. It excels at tasks like summarization and classification. You have to set a reasoning effort with GPT-5.4 nano. The lower the reasoning effort, the faster and more affordable it will be.

• GPT-5.4 nano inputs: Text, images

• GPT-5.4 nano outputs: Text

• GPT-5.4 nano context window: 400,000 tokens

• GPT-5.4 nano input pricing: $0.20/M tokens

• GPT-5.4 nano output pricing: $1.25/M tokens

Superseded

GPT 5 launched in August 2025, followed by GPT 5.1 in November. 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 (days after GPT-5.3), it was quickly superseded. Since then, they’ve all been superseded by GPT 5.6, but all these models are still available in the API (there are also Pro versions of them available). GPT-5.4 pricing is below for context, but check out the API docs to see the accurate pricing of all the older models.

• GPT-5.4 inputs: Text, images

• GPT-5.4 outputs: Text

• GPT-5.4 context window: 1M token

• GPT-5.4 input pricing: $2.50/M tokens

• GPT-5.4 output pricing: $15/M tokens

Superseded

GPT-5 mini was a faster and more affordable alternative to GPT-5.

• 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

Superseded

GPT-5 nano was OpenAI’s fastest and most affordable alternative to GPT-5.

• 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

Superseded

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-5.5 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

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

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

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

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

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

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

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

Best OpenAI model for generating images

GPT Image 2 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 and GPT Image 1.5.

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 2 inputs: Text, images

• GPT Image 2 outputs: Images

• GPT Image 2 input pricing: $5/M text tokens; $8/M image tokens

• GPT Image 2 output pricing: $30/M image tokens

Superseded

GPT Image 1.5 was the successor to OpenAI’s DALL·E image models. It’s now been superseded.

• GPT Image 1.5 inputs: Text, images

• GPT Image 1.5 outputs: Images

• GPT Image 1.5 input pricing: $5/M text tokens; $8/M image tokens

• GPT Image 1.5 output pricing: $10/M text tokens; $32/M image tokens

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

• Sora 1

• Sora 2

• GPT Image 1

While most of these have been replaced or superseded by newer models, it’s noteworthy that there’s been no announced replacement for OpenAI’s now-deprecated Sora text-to-video models. This may change in the coming months.

How to choose the right OpenAI model

OpenAI has lots of models, but they each serve a purpose. GPT-5.6 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.

Use OpenAI models in your existing workflows

OpenAI’s models are most useful when they’re woven into the work you’re already doing—not sitting in a separate chat window you have to context-switch to. Zapier connects GPT-5.6 and the rest of OpenAI’s model lineup to 9,000 apps, so your agents can act on real data in the tools your business actually runs on.

You can add AI steps to your deterministic workflows—some models are built in, so you don’t even need an OpenAI account. That means things like automatically triaging support tickets, generating CRM summaries when a deal moves stages in Salesforce, or drafting a Slack message whenever a form submission comes in. And because Zapier handles OAuth for every connected app, your credentials never touch the model’s context.

Or you can install Zapier in any AI assistant—like Claude, ChatGPT, or Cursor—or the terminal with a single command. From there, your AI can take real actions across your stack without ever leaving the chat window. Learn more about how to use OpenAI models with Zapier, or get started with one of these pre-made templates.

Related reading:

This article was originally published in May 2025. The most recent update was in July 2026.