GPT Image 2 is our latest image generation model, with better instruction following and adherence to prompts.

gpt-image-2

Sets a general size parameter used by selected models or generators.

Controls how many candidate responses are generated for one request.

Sets the output quality level, usually trading speed for fidelity.

GPT-6.1 Sol balances intelligence and cost for coding and agentic workflows. 1,050,000-token context window with 128,000 max output tokens and reasoning effort control (low, medium, high, xhigh, max).

gpt-6.1-sol

Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

Enables parallel execution of tools, allowing multiple tools to run simultaneously.

Controls the level of reasoning used by the model.

Defines the format or type of the generated response.

Sends the response in real-time as it's being generated.

Decides whether to use tools or just the model for generating responses.

Lists tool definitions or capabilities available to the model.

GPT-6 Luna is OpenAI's most efficient GPT-6 model, built for high-volume tasks. 1,050,000-token context window with 128,000 max output tokens and reasoning effort control.

gpt-6-luna

GPT-6 Sol balances intelligence and cost for coding and agentic workflows. 1,050,000-token context window with 128,000 max output tokens and reasoning effort control.

gpt-6-sol

GPT-6 Astra is OpenAI's most capable broadly deployed model, built for the hardest end-to-end work. It excels at complex reasoning, coding, computer use, research, and document creation, and is OpenAI's first model to reach the Critical level of cybersecurity capability under its Preparedness Framework.

gpt-6-astra

GPT-5.6 Terra balances intelligence and cost in the GPT-5.6 family. 1.05M context, knowledge cutoff Feb 2026.

gpt-5.6-terra

Specifies the maximum number of tokens allowed in a response.

Sends the response in real-time as it is being generated.

GPT-5.6 Sol is OpenAI's flagship frontier model for complex reasoning and professional work. 1.05M context, knowledge cutoff Feb 2026.

gpt-5.6-sol

GPT-5.6 Luna is OpenAI's fastest and most affordable model in the GPT-5.6 family. Built for high-volume, latency-sensitive workloads like chat, classification, and lightweight agentic tasks, it delivers strong reasoning at the lowest cost in the lineup — with a 1M+ token context window and 128K max output.

gpt-5.6-luna

Controls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.

GPT-5.4 is our most advanced general-purpose model in the GPT-5 family. Optimized for complex reasoning, long-context agentic workflows, multimodal processing, and superior code generation.

gpt-5.4

Controls how much reasoning effort the model applies before generating a response.

Controls the level of detail and length of the generated responses.

GPT-5.4 nano is an ultra-fast, low-cost model optimized for simple tasks, high-scale automation, and lightweight tool usage.

gpt-5.4-nano

GPT-5.4 mini is a fast, cost-efficient, tool-capable model designed for scalable agent workflows and real-time automation.

gpt-5.4-mini

GPT-5.5 is OpenAI's most advanced frontier model, optimized for complex real-world work including agentic reasoning, long-context workflows, tool use, and high-performance code generation. It can plan, execute, and complete multi-step tasks with minimal guidance while maintaining strong context over long durations.

gpt-5.5

GPT-5.2 is our best general-purpose model, part of the GPT-5 flagship model family. Our most intelligent model yet for both general and agentic tasks

gpt-5.2

Controls how concise or detailed the generated response should be.

GPT-5.1 is a frontier-grade OpenAI model with stronger general-purpose reasoning and better instruction following than GPT-5. It accepts text and image inputs and produces text outputs.

gpt-5.1

GPT-5-nano model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

gpt-5-nano

GPT-5-mini model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

gpt-5-mini

GPT-5 model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

gpt-5

GPT-4o ("o" for "omni") is a fast, general-purpose multimodal model. It accepts both text and image inputs, and produces text outputs.

gpt-4o

GPT-4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.

gpt-4.1-mini

GPT-4o mini (“o” for “omni”) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.

gpt-4o-mini

GPT-4.1 is our flagship model for complex tasks. It is well suited for problem solving across domains.

gpt-4.1

gpt-4o-2024-08-06 model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

gpt-4o-2024-08-06

gpt-4o-mini-2024-07-18 is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.

gpt-4o-mini-2024-07-18

GPT Image 2.5 Flare is OpenAI's fast, everyday image generation and editing model, accepting text and image input and returning images. Supports the image generation and image edit endpoints.

gpt-image-2.5-flare

GPT Image 2.5 Sunburst is OpenAI's most capable image generation and editing model, accepting text and image input and returning images. Strong editing precision with inpainting support. Default snapshot gpt-image-2.5-sunburst-2026-09-08.

Model	Context	Max output	Input	Output	Capabilities
gpt-6.1-sol Chat	1.1M	128K	$2.00	$10.00	Vision, Files, Tools, System prompt, Reasoning
gpt-6-luna Chat	1.1M	128K	$0.10	$0.50	Vision, Files, Tools, System prompt, Reasoning
gpt-6-sol Chat	1.1M	128K	$2.00	$10.00	Vision, Files, Tools, System prompt, Reasoning
gpt-6-astra Chat	1.1M	128K	$10.00	$50.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5.6-terra Chat	1.1M	128K	$2.00	$12.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5.6-sol Chat	1.1M	128K	$4.00	$20.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5.6-luna Chat	1.1M	128K	$0.20	$1.20	Vision, Files, Tools, System prompt, Reasoning
gpt-5.4 Chat	1.1M	128K	$2.50	$15.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5.4-nano Chat	400K	128K	$0.20	$1.25	Vision, Files, Tools, System prompt, Reasoning
gpt-5.4-mini Chat	400K	128K	$0.75	$4.50	Vision, Files, Tools, System prompt, Reasoning
gpt-5.5 Chat	1.1M	128K	$5.00	$30.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5.2 Chat	400K	128K	$1.75	$14.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5.1 Chat	400K	128K	$1.25	$10.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5-nano Chat	400K	128K	$0.05	$0.40	Vision, Files, Tools, System prompt, Reasoning
gpt-5-mini Chat	400K	128K	$0.25	$2.00	Vision, Files, Tools, System prompt, Reasoning
gpt-5 Chat	400K	128K	$1.25	$10.00	Vision, Files, Tools, System prompt, Reasoning
gpt-4o Chat	128K	16K	$2.50	$10.00	Vision, Tools, System prompt
gpt-4.1-mini Chat	1.0M	33K	$0.40	$1.60	Vision, Files, Tools, System prompt
gpt-4o-mini Chat	128K	8K	$0.15	$0.60	Vision, Files, Tools, System prompt
gpt-4.1 Chat	1.0M	33K	$2.00	$8.00	Vision, Files, Tools, System prompt
gpt-4o-2024-08-06 Completion	128K	16K	$2.50	$10.00	Vision, Tools, System prompt
gpt-4o-mini-2024-07-18 Completion	128K	8K	$0.15	$0.60	Vision, Tools, System prompt
gpt-image-2.5-flare Image	—	—	—	—	Vision
gpt-image-2.5-sunburst Image	—	—	—	—	Vision

gpt-image-2

Start building today