Original post · Original
The article text is unavailable in this language; an existing version is shown.
The most practical video AI right now puts a number on what it sees, a video goes in, a probability comes out
And AI/ML API (@aimlapi) now offers HeyGen’s newly released Decision 1 model.
Decision 1 model never writes a single word. You show it text, images, video or audio, ask it up to 400 questions, and it answers each one with a probability your code can act on.
Introducing @HeyGen Decision 1 on AI/ML API with 50% off 🔥
It analyzes the video and turns gestures and emotions into emojis. 8 out of 8 right for just $0.0027
Try it on -> https://t.co/wFX5XRmB47 https://t.co/3j0nSSrK51
View this post on X ↗
New from HeyGen Research: Decision 1
Ask anything about video, audio, image or text, and get calibrated answers in ~100 ms.
→ 4x faster than Gemini
→ Best calibrated of 5 models
→ 400 questions per call
Turbo: $0.042 / 1M input tokens
Decision 1: $0.07 / 1M input tokens https://t.co/4jQOEgxAGj
View this post on X ↗