Veo 3.1 和 Gemini 图像模型现已通过 OpenAI 兼容层可用

Veo 3.1 and Gemini image models are now available through the OpenAI compatibility layer, no SDK swap needed. 🎬 Generate videos via/v1/videos using Veo 3.1

🍌 Generate images with Nano Banana viaimages.generate

🔌 Drop-in compatible with OpenAI Python and JS SDKs

🔀 Switch to Gemini API by changing just 3 lines of code

!Image 2: Tweet image

8 Replies

9 Retweets

104 Likes

5,206 Views 

One Sentence Summary

Google DeepMind announces that Veo 3.1 video generation and Gemini image models are now accessible through OpenAI's compatibility layer, requiring no SDK changes.

Summary

This announcement reveals that Google's Veo 3.1 video generation model and Gemini image models (including Nano Banana) are now available through OpenAI's API compatibility layer. Developers can generate videos via the /v1/videos endpoint and create images using the images.generate method. The integration offers drop-in compatibility with existing OpenAI Python and JavaScript SDKs, allowing users to switch to the Gemini API by modifying just 3 lines of code. This represents a significant step in making Google's AI models more accessible to developers already familiar with OpenAI's API structure.

AI Score

82

Influence Score 28

Published At Yesterday

Language

English

Tags

Veo 3.1

Gemini

Google DeepMind

OpenAI Compatibility

AI Models