Quick Start
- 1
- 2Use the fal API SDK or REST API to call
openai/gpt-image-2— see the documentation for request format.
Code Examples
About fal API
fal serves asynchronous and real-time model APIs on its infrastructure with queue handling, automatic scaling, SDK and HTTP access, and model-specific output-based billing. Its public catalog includes first-party and partner-hosted endpoints across image, video, audio, vision, and 3D generation; model cards expose the applicable schema, pricing, and license information.
fal API is a developer platform for calling a large catalog of production-ready image, video, audio, vision, 3D, and multimodal generation models through a unified API surface.
Pricing on fal API
Capabilities
About GPT Image 2
OpenAI's image generation model succeeding DALL-E 3, released April 21, 2026. Uses an autoregressive architecture with native reasoning — the model plans structure and composition before generating pixels. Supports up to 4K (4096×4096) resolution, achieves ~99% character-level text accuracy across Latin, CJK, Hindi, and Bengali scripts, and generates images ~2× faster than DALL-E 3. Debuted at #1 on the Image Arena leaderboard by a +242-point margin. Powered by the GPT-5.4 backbone. API: $8/M image input tokens, $2/M cached, $30/M image output tokens. ChatGPT GA April 22, 2026; API access May 2026.