GPT-image-2
GPT-image-2 is a multimodal model from OpenAI, released on 2026-04-21. It accepts text and image input and returns image output. The recorded context window is 32K. Cataloged capabilities include Reasoning model and Multilingual. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $5.00/ 1M tokens | $10.00/ 1M tokens |
| Image | - | $8.00/ 1M tokens | $30.00/ 1M tokens |
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | - | — | $1.25/ 1M tokens |
| Image | - | — | $2.00/ 1M tokens |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
GPT-image-2 is a multimodal model from OpenAI, released on 2026-04-21.
It accepts text and image input and produces image output. Its cataloged capabilities include Reasoning model and Multilingual. The recorded context window is 32K.
The model weights are proprietary and are not published for download. The page records 6 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment. The page links 1 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.
GPT-image-2 is a multimodal model from OpenAI, released on 2026-04-21. It accepts text and image input and returns image output. The recorded context window is 32K. Cataloged capabilities include Reasoning model and Multilingual. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.
The current model record lists text and image as input and image as output.
The recorded context window is 32K. Fields without a source-backed value remain undisclosed.
The page records 6 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment.
Image-generation model; the current text/agent benchmark catalog is not applicable.
The model weights are proprietary and are not published for download. Review the linked license text before commercial or derivative use.
Follow DataLearner on WeChat for AI model updates and research notes.
