OpenRouter, a platform for accessing AI models, added image generation and editing with Google DeepMind’s Gemini 2.5 Flash Image Preview in August 2025. Its announcement describes generating multiple images in one request and maintaining characters across scenes. That opened a workflow for producing related visual assets, such as comic panels or logo variations, through the platform. The milestone was OpenRouter’s first image model; the post’s title refers to that platform launch, not the invention of AI image generation.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
