GPT Image Models by OpenAI
Last refreshed 2026-10-17. Next refresh: weekly.
Capabilities
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.
Decision facts
- Best fit
- image generationvision and multimodal workreasoning
- Capability starting point
- GPT Image 2.5 Sunburst with reasoning and multimodal inputs
- Lowest tracked input
- GPT Image 1 Mini · $2.00/1M · Vercel AI Gateway
- Closest related family
- GPT-5
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs image generation, reasoning, and multimodal inputs.
Use when the workload needs image generation, reasoning, and multimodal inputs.
Use when the workload needs image generation, reasoning, and multimodal inputs.
Use when the workload needs image generation and multimodal inputs.
Use when the workload needs image generation and multimodal inputs.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT Image 2.5 Flare | Use when the workload needs image generation, reasoning, and multimodal inputs. | 2026-09 | image generationreasoningmultimodal inputs | Current |
| GPT Image 2.5 Sunburst | Use when the workload needs image generation, reasoning, and multimodal inputs. | 2026-09 | image generationreasoningmultimodal inputs | Current |
| GPT Image 2 | Use when the workload needs image generation, reasoning, and multimodal inputs. | 2026-04 | image generationreasoningmultimodal inputs | Current |
| chatgpt-image-latest | Use when the workload needs multimodal inputs. | 2025-12 | multimodal inputs | Current |
| GPT Image 1.5 | Use when the workload needs image generation and multimodal inputs. | 2025-12 | image generationmultimodal inputs | Current |
| GPT Image 1 Mini | Use when the workload needs image generation and multimodal inputs. | 2025-10 | image generationmultimodal inputs | Current |
Release Timeline
5 release groupsReplaced By
Keep for legacy integrations; evaluate GPT Image 1.5 before new work.
Specifications(7 models)
| Model | Released | Vision | Multimodal | Reasoning |
|---|---|---|---|---|
| GPT Image 2.5 Flare | 2026-09 | Yes | Yes | Yes |
| GPT Image 2.5 Sunburst | 2026-09 | Yes | Yes | Yes |
| GPT Image 2 | 2026-04 | Yes | Yes | Yes |
| chatgpt-image-latest | 2025-12 | No | Yes | No |
| GPT Image 1.5 | 2025-12 | Yes | Yes | No |
| GPT Image 1 Mini | 2025-10 | Yes | Yes | No |
Available From(3 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 2.5 Flare | OpenAI API | $5 | $30 | Serverless |
| GPT Image 2.5 Sunburst | OpenAI API | $5 | $30 | Serverless |
| GPT Image 1.5 | OpenAI API | $8 | $32 | Serverless |
| GPT Image 2 | OpenAI API | $8 | $30 | Serverless |
Models(7)
GPT Image 2.5 Flare
GPT Image 2.5 Sunburst
GPT Image 2
chatgpt-image-latest
GPT Image 1.5
GPT Image 1 Mini