AI BriefingOpenAI Unveils Latest Image Generation Model via API
Key point
OpenAI has released gpt-image-1, a model that provides ChatGPT's multimodal capabilities through the API.
Details
OpenAI is releasing via API the native multimodal model used in ChatGPT. The new model, gpt-image-1, enables developers and enterprises to easily integrate high-quality, professional-grade image generation capabilities into their own tools and platforms.
The model features diverse style implementation, adherence to user guidelines, extensive world knowledge, and accurate text rendering capabilities. Companies such as Adobe, Canva, GoDaddy, HubSpot, Instacart, and invideo are already using it to develop services such as design, logo creation, marketing asset generation, and video editing.
For safety, it includes C2PA metadata, and developers can adjust filtering strength via the moderation parameter. Additionally, by default, customer API data is not used for model training.
Costs are set on a per-token basis.
- Text input tokens: $5 per 1M tokens
- Image input tokens: $10 per 1M tokens
- Image output tokens: $40 per 1M tokens
Actual generation costs range from about $0.02 (low quality) to $0.19 (high quality) per image, depending on quality.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Comfy Launches Comfy Router: A Unified API for Frontier Media Models