Veo 3.1

Overview

Veo 3.1 is Google’s video generation model, referenced in product updates focused on stronger creative control and higher-quality output. Across newsletter mentions, the model’s notable improvements include portrait mode support, better visual consistency across characters, objects, and backgrounds, and upscaling to 1080p and 4K. It has been surfaced through Google products including the Gemini app and Flow by Google, and later exposed through an OpenAI compatibility layer for easier developer adoption.

For AI Product Managers, Veo 3.1 matters because it shows how video generation is moving from demo-quality outputs toward more production-oriented workflows. Features like aspect-ratio flexibility, consistency across scenes, and higher-resolution upscaling directly affect usability for marketing, creator tools, brand content, and multimodal product experiences. Its availability through familiar API patterns also lowers integration friction for teams already building around OpenAI-style interfaces.

Key Developments

• 2026-01-14 — Google AI announced Veo 3.1 support for portrait mode, enhanced visual consistency across characters, objects, and backgrounds, and state-of-the-art upscaling to 1080p and 4K.
• 2026-01-15 — Demis Hassabis highlighted Veo 3.1 improvements including enhanced expressiveness, portrait mode support, and 1080p and 4K upscaling, rolling out in the Gemini app and Flow by Google.
• 2026-03-21 — Philipp Schmid shared that Veo 3.1 video and Gemini image models were available as drop-in options via the OpenAI compatibility layer, with video generation accessible through `/v1/videos`.

Relevance to AI PMs

• Design for real-world video use cases: Portrait mode support makes Veo 3.1 more relevant for mobile-first content, social formats, and creator workflows. PMs can use this to evaluate product fit for vertical video and platform-specific publishing.
• Improve output reliability in user-facing experiences: Better visual consistency across characters, objects, and backgrounds is important for multi-scene storytelling, branded content, and repeatable generation flows. PMs should track this as a quality metric when comparing vendors or defining acceptance criteria.
• Reduce integration risk and speed adoption: Availability through an OpenAI compatibility layer means teams may be able to test or switch to Veo 3.1 with less engineering overhead. PMs can use this to run faster experiments, benchmark performance, and negotiate architecture choices around multimodal APIs.

Related

• Gemini — Closely connected as part of Google’s broader generative AI ecosystem and referenced alongside Veo 3.1 in multimodal workflows.
• OpenAI compatibility layer — Important for developers because it enables drop-in access to Veo 3.1 through familiar API conventions such as `/v1/videos`.
• Nano Banana — Mentioned alongside Veo 3.1 as a Gemini image model, suggesting paired image-and-video generation workflows.
• Philipp Schmid — Shared the update about Veo 3.1 becoming available via the compatibility layer.
• Demis Hassabis — Highlighted product improvements including expressiveness, portrait mode, and high-resolution upscaling.
• Google AI / Google — The organization behind Veo 3.1 and the source of the product announcements.
• Gemini app — One of the rollout surfaces where Veo 3.1 improvements became available.
• Flow by Google — Another Google product surface where Veo 3.1 was rolled out.
• Portrait mode — A major feature update that expands Veo 3.1’s relevance for mobile and social content creation.
• Visual consistency — A core quality improvement that matters for coherent video generation across scenes and assets.