The API currently lacks output customization options, such as altering image quality, size, or style, although xAI suggests future updates may include these features. Designed to be user-friendly, the API revises text prompts for clarity before generating images. While it is compatible with OpenAI’s SDK, it does not support the Anthropic SDK, which may limit some integrations. The introduction of the Aurora image generation model, based on a mixture of experts network, has facilitated this new tool aimed at developers.
Key takeaways:
- xAI has launched a new API, 'grok-2-image-1212', for generating images from text prompts, marking a significant step forward for the company.
- The API allows developers to generate up to 10 images per request, with a limit of five requests per second, and outputs images in JPEG format.
- Priced at $0.07 per image, the API is more expensive than some competitors but cheaper than others, and currently does not support output customisation.
- The API is designed to be user-friendly and efficient, with compatibility for OpenAI's SDK but not Anthropic's, potentially limiting some integrations.