All models
Image generationLive
OpenAIGPT-Image-2
OpenAI's current image model for detailed generation and editing, especially complex prompts, text-heavy visuals, and high-fidelity source images.
Plain-English overview
What GPT-Image-2 actually is
GPT-Image-2 accepts text and images and produces images through OpenAI's image endpoints. It is aimed at high prompt adherence and detailed compositions rather than a single fixed style.
Cost varies sharply by quality and output size. A low-quality square image can be inexpensive, while a high-quality or 4K output costs many times more. Compare using the setting you will actually ship.
Good fit for
- Text-heavy graphics and infographics
- Product and brand image editing
- High-resolution creative workflows
Category comparison
The facts that matter for image models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Typical price basis
- OpenAI: $2.50 text input · $4 image input · $15 image output / 1M tokensA representative current provider price with its quality or resolution basis.
- Maximum output
- Up to about 4K / 8.29MP on falMaximum documented resolution or pixel area for the listed route.
- Core tasks
- Generation and editingWhether the model supports generation, editing, or both.
- Reference images
- High-fidelity image inputHow the model can use images to guide or edit an output.
- Text & layout
- Designed for detailed text-heavy imagesProvider-documented positioning for typography and structured composition.
- API access
- OpenAI, falDirect and notable third-party routes included in this guide.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Example output: square 1,024 × 1,024 images. Prices depend on supported resolution and quality; edits and retries can cost extra.
GPT-Image-2
OpenAI
Pricing & comparisons
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get GPT-Image-2
Availability
Regions and access stage
Available through OpenAI's Images API and as a partner model on fal.
Direct OpenAI access follows OpenAI's live supported-country list; fal availability follows its own terms.
Check live availabilityData and training
The route matters.
For direct OpenAI API use, API content is not used for training by default and standard retention controls apply. fal stores request input/output by default, but its no-store header can prevent payload storage; uploaded CDN files require separate handling.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
GPT-Image-2 FAQ
What is GPT-Image-2?
OpenAI's current image model for detailed generation and editing, especially complex prompts, text-heavy visuals, and high-fidelity source images. GPT-Image-2 accepts text and images and produces images through OpenAI's image endpoints. It is aimed at high prompt adherence and detailed compositions rather than a single fixed style.
When was GPT-Image-2 released?
GPT-Image-2 was released on April 21, 2026 according to the cited provider materials.
Where can I access GPT-Image-2?
Available through OpenAI's Images API and as a partner model on fal. The access routes listed in this guide are OpenAI and fal.
How much does GPT-Image-2 cost?
$2.50 text input · $4 image input · $15 image output / 1M tokens. OpenAI standard rates. Cached text input is $0.625 per million tokens and cached image input is $1 per million. Partner pricing can use a different per-image basis, and total direct-API cost depends on token consumption.
Where is GPT-Image-2 available?
Available through OpenAI's Images API and as a partner model on fal. Direct OpenAI access follows OpenAI's live supported-country list; fal availability follows its own terms.
Is my GPT-Image-2 API data used for training?
For direct OpenAI API use, API content is not used for training by default and standard retention controls apply. fal stores request input/output by default, but its no-store header can prevent payload storage; uploaded CDN files require separate handling. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
GPT-Image-2 vs GPT-Image-2.5 Sunburst
OpenAI's quality-first GPT Image 2.5 model for demanding generation, precise edits, subject preservation, typography, and high-resolution creative work.
Open full comparisonGPT-Image-2 vs GPT-Image-2.5 Flare
OpenAI's speed-first GPT Image 2.5 model for everyday generation and editing, positioned at GPT Image 2-level image quality with lower latency.
Open full comparisonGPT-Image-2 vs Nano Banana 2
Google's versatile image workhorse for fast generation, conversational edits, multiple references, grounded imagery, and outputs up to 4K.
Open full comparisonGPT-Image-2 vs FLUX.2 Pro
Black Forest Labs' production-focused image model for scalable generation and editing, precise composition, and multi-reference creative workflows.
Open full comparisonGPT-Image-2 vs Ideogram 4.0
A design-oriented image model with open weights, multilingual typography, structured layout control, editable elements, and simple per-image API tiers.
Open full comparisonGPT-Image-2 vs Grok Imagine Image 2.0
SpaceXAI's current image model for creating and editing practical visuals, with an emphasis on following detailed instructions, typography, and consistent references.
Open full comparisonGPT-Image-2 vs MAI-Image-2.5 Pro
Microsoft's quality-focused image generation and editing model for Azure teams that want enterprise deployment controls inside Microsoft Foundry.
Open full comparisonGPT-Image-2 vs Midjourney V8.2
Midjourney's current default image model for highly polished, style-led creative work, with stronger personalization and a new reference-based Edit Model.
Open full comparisonGPT-Image-2 vs Reve 2.1
A typography-aware image model for creating and editing polished visuals, now available through Reve's creative product rather than its discontinued direct API.
Open full comparison
