Models
Image, video and audio models behind one API. Each task costs the price of the route that serves it, and failed tasks are free.
MiniMax H3
Base · Character · Native · Upscale
MiniMax H3 turns text, images or references into video with sound. Call it through one API in three variants, Base, Character and Native, and upscale a finished video to twice its resolution.
GPT Image 2
gpt-image-2
GPT Image 2.5
Flare · Sunburst
GPT Image 2.5 is OpenAI's model for making and editing images from a prompt and reference images. Flare is the fast choice for most work; Sunburst takes longer but is stronger at edits and at keeping reference subjects.
GPT Image 2.6
Flare · Sunburst
GPT Image 2.6 is the newest version of OpenAI's model for making and editing images from a prompt and reference images. It comes in two variants, Flare and Sunburst, that take the same parameters at the same price, so you can try both and keep the one you like.
Nano Banana 2
nano-banana-2
Nano Banana 2.1
nano-banana-2.1
Nano Banana Pro
nano-banana-pro