GPT Image Models by OpenAI
5 models2025–2026From $2/1M input
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use with conditions
Models5
Released2025–2026
Capabilities
Vision4 of 5 models
MultimodalAll models
Reasoning1 of 5 models
Links
WebsiteAbout
OpenAI's GPT Image family is the successor to DALL-E, bringing autoregressive architecture and native reasoning capabilities to image generation. GPT Image models reason about structure before drawing, unlike diffusion-based predecessors. GPT Image 2 launched April 2026 as the default image model in ChatGPT.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view1 retired
GPT Image 2Current
Use when the workload needs image generation, reasoning, and multimodal inputs.
2026-04image generationreasoningmultimodal inputs
GPT Image 1.5Current
Use when the workload needs image generation and multimodal inputs.
2025-12image generationmultimodal inputs
GPT Image 1 MiniCurrent
Use when the workload needs image generation and multimodal inputs.
2025-10image generationmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT Image 2 | Use when the workload needs image generation, reasoning, and multimodal inputs. | 2026-04 | image generationreasoningmultimodal inputs | Current |
| GPT Image 1.5 | Use when the workload needs image generation and multimodal inputs. | 2025-12 | image generationmultimodal inputs | Current |
| chatgpt-image-latest | Use when the workload needs multimodal inputs. | 2025-12 | multimodal inputs | Current |
| GPT Image 1 Mini | Use when the workload needs image generation and multimodal inputs. | 2025-10 | image generationmultimodal inputs | Current |
Release Timeline
4 release groups2026-04
1 current
GPT Image 2
Currentimage generationreasoningmultimodal inputs
2025-12
2 current
chatgpt-image-latest
Currentmultimodal inputs
GPT Image 1.5
Currentimage generationmultimodal inputs
2025-10
1 current
GPT Image 1 Mini
Currentimage generationmultimodal inputs
2025-04
1 retired
GPT Image 1
Replacedimage generationmultimodal inputs
Replaced By
Replaced
Keep for legacy integrations; evaluate GPT Image 1.5 before new work.
Specifications(5 models)
| Model | Released | Vision | Multimodal | Reasoning |
|---|---|---|---|---|
| GPT Image 2 | 2026-04 | Yes | Yes | Yes |
| GPT Image 1.5 | 2025-12 | Yes | Yes | No |
| chatgpt-image-latest | 2025-12 | No | Yes | No |
| GPT Image 1 Mini | 2025-10 | Yes | Yes | No |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT Image 1 Mini | Vercel AI Gateway | $2 | $8 | Serverless |
| chatgpt-image-latest | OpenAI API | $5 | $10 | Serverless |
| GPT Image 1.5 | Vercel AI Gateway | $5 | $32 | Serverless |
| GPT Image 2 | Vercel AI Gateway | $5 | $30 | Serverless |
| GPT Image 1.5 | OpenAI API | $8 | $32 | Serverless |
| GPT Image 2 | OpenAI API | $8 | $30 | Serverless |
Frequently Asked Questions
- What is GPT Image used for?
- GPT Image is used for image generation, vision and multimodal work, and reasoning. The family description and listed model capabilities point to those workloads as the best fit.
- How does GPT Image compare to GPT Realtime 2?
- GPT Image by OpenAI is strongest where you need image generation, while GPT Realtime 2 by OpenAI is the closest related family to check for realtime voice. GPT Image has 5 listed variants, while GPT Realtime 2 reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which GPT Image model should I use?
- For the lowest listed input price, start with GPT Image 1 Mini through Vercel AI Gateway at $2/1M input tokens. For the most capable/latest local choice, evaluate GPT Image 2 with reasoning and multimodal inputs.
