
We've added a bunch of cool new image, video and audio models: GPT Image 2.6, Gemini Omni Flash 1.2, Kling 4.0 Flash, VEED Dubbing and ElevenLabs Music v2.5. Every sample was made with the model it's under, starring faces from our model agency.
GPT Image 2.6
OpenAI's newest image model is now Glif's default: better at text and at keeping characters consistent, same price as 2.5, and backgrounds are solid unless you ask for a transparent one.






Gemini Omni Flash 1.2
Google's newest video model makes clips with sound from text or an image. You can now pick a length from 3 to 15 seconds, and it's about 31% cheaper than 1.1. Both samples use the same prompts as the Kling 4.0 Flash clips below, so you can compare.
Kling 4.0 Flash
The fast, cheap Kling 4.0: 720p clips of 3 to 20 seconds for about 40% less, and if you put a line of dialogue in quotes, the character says it.
VEED Dubbing
Dubs a video into another language in the speaker's own voice, with lips synced to the new words, and Pro adds accents like Mexican Spanish.
🇺🇸 English
🇩🇪 German
🇲🇽 Spanish
ElevenLabs Music v2.5
The newest ElevenLabs music model writes songs with lyrics, instrumentals and background music for about 20 credits a minute, and plans written for v1 still work.

0:00/0:00

0:00/0:00

0:00/0:00
Tell us what you make with them on X!




