GPT-5.4 Image 2
GPT-5.4 Image 2 is a multimodal model made by OpenAI, added to the catalog on 21 Apr 2026. It has a context window of 272,000 tokens and costs $8.00 per 1M input tokens and $15.00 per 1M output tokens. It accepts text, images and files and produces text and images. Typical uses: creating images from text prompts, discussing supplied images and working with files and written instructions.
Price checked ยท source: OpenRouter
What GPT-5.4 Image 2 is
OpenAI: GPT-5.4 Image 2 is a multimodal model that combines GPT-5.4 with image generation capabilities from GPT Image 2, according to its catalog description. It accepts text, images, and files, and can produce both text and images. This allows workflows to include written prompts or supplied visual and file inputs, with textual or image output. The catalog also lists reasoning as a supported capability, alongside structured outputs and response-format support.
The model has a context length of 272,000 tokens and a maximum output of 128,000 tokens. Its context capacity can suit work that brings substantial source material into a single interaction, while its output limit allows for extended responses or generated content in its supported output types. Its listed capabilities make it relevant to tasks that combine text or image inputs with written or visual output. Examples include discussing supplied images, creating images from text-led requests, working with files alongside written instructions, and producing structured text. The facts identify input and output modalities and supported features, but do not specify particular file formats, image-generation controls, or the exact behavior of structured output. Its multimodal inputs, text-and-image outputs, long context, and reasoning support are the main capabilities to consider when assessing its fit for a task.
Key features
- Accepts text, image, and file inputs
- Produces both text and images
- Has a context length of 272,000 tokens
- Supports reasoning, structured outputs, and response formats
Typical uses
- Creating images from text prompts
- Discussing supplied images
- Working with files and written instructions
- Producing structured text
- Combining long source material with image generation
GPT-5.4 Image 2 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $8.00 |
| Output, per 1M tokens | $15.00 |
| Cached input read, per 1M tokens | $2.00 |
| Web search, per search | $0.01 |
No price change since it was added on 21 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0085 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.212 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.270 |
| Read a 300-page contract set150,000 in / 1,500 out | $1.22 |
GPT-5.4 Image 2 specifications
| Model id | openai/gpt-5.4-image-2 |
|---|---|
| Version | gpt-5.4-image-2-20260421 |
| Context window | 272,000 tokensAbout 204,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 21 Apr 2026 |
| Input types | image, text, file |
|---|---|
| Output types | image, text |
| Tool calling | No |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for GPT-5.4 Image 2 yet.
Compare GPT-5.4 Image 2
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.