OpenAI / GPT Image 2
openai/gpt-image-2
OpenAI
openai
GPT Image 2 is OpenAI's state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs.
Run predictions with the official JavaScript SDK. Use your API key from Settings.
This model may apply different rates depending on input fields (for example tokens, seconds, megapixels, or prediction type). The effective price uses the first matching rule when you run a prediction.
Pricing formula
OpenAI image token billing.
Rates (USD / 1M)
Estimation parameters
| Rule | Condition | Rate |
|---|---|---|
Base pricing Default pricing when no criteria match | — | $0.02 / token |
Image-to-image: client sent one or more reference images — adjust USD per 1M for buckets you care about. | input_images not empty | image input: $10.00 / 1M · text input: $5.25 / 1M |
Text-to-image only (no input_images or empty array) — restore baseline rates for this path. | input_images empty | image input: $8.00 / 1M · text input: $5.00 / 1M |
Portrait output | size == 1024x1536 | image output: $32.00 / 1M |
Landscape output | size == 1536x1024 | image output: $32.00 / 1M |
Square output | size == 1024x1024 | image output: $30.00 / 1M |
WebP output | output_format == webp | text input: $5.50 / 1M |