Google Opens Veo 3 to Developers via Gemini API in Paid Preview
Veo 3 was unveiled at Google I/O 2025 and is capable of producing high-fidelity, cinematic-quality videos.
Google CEO Sundar Pichai has announced that developers can now access Veo 3, the company’s latest text-to-video generation model, through the Gemini API in a paid preview.
“Developers can now build with Veo 3 🎬 in the Gemini API,” Pichai wrote on X. “It’s live in paid preview, starting with text to video (image to video coming soon). So many fun Veo trends coming from @Geminiapp users already, can't wait to see what devs come up with!”
Veo 3 was unveiled at Google I/O 2025 and is capable of producing high-fidelity, cinematic-quality videos from simple text prompts. The addition to the Gemini API now allows developers to start experimenting and building creative video experiences, powered by Google’s multimodal large language model stack.
While the current version supports text-to-video, Google said image-to-video capabilities will be added soon, broadening the scope for creators, developers, and marketers alike.
Earlier this year, Google confirmed that the company is using a portion of YouTube’s vast video library to train Veo 3.
While only a subset of content is used, the practice has raised concerns among creators, many of whom say they were unaware their videos could be used to train AI models that may eventually compete with them.
Last month, Google announced that Veo 3 is available in public preview on Vertex AI.
Comments ()