Sign in
← AI PulseAug 14, 2026

Wire · news · Multi-source brief

Vercel AI SDK Adds Grok Imagine Video 1.5 and Gemini 3.7 Flash Support

The Vercel AI SDK now supports Grok Imagine Video 1.5 for text-to-video and image-to-video generation, alongside the addition of the Gemini 3.7 Flash model.

By Illumora Editorial

Source · Aug 14, 2026, 6:28 AM · On Illumora · Aug 14, 2026, 6:32 AM

Media from the primary source — shown here so you can stay on Illumora.

Synthesized from multiple allowlisted primaries on the same event. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →Vercel AI SDK Changelog — Release @ai-sdk/xai@3.0.121 · vercel/ai
Save

The Vercel AI SDK has been updated to include support for Grok Imagine Video 1.5 and the Gemini 3.7 Flash model. The @ai-sdk/xai@3.0.121 release introduces Grok Imagine Video 1.5, enabling text-to-video and image-to-video capabilities with native 1080p resolution. Separately, the @ai-sdk/google@2.0.88 and @ai-sdk/google-vertex@3.0.163 releases add the Gemini 3.7 Flash model.

Key Points

  • The @ai-sdk/xai@3.0.121 release adds support for the grok-imagine-video-1.5 model ID.
  • Grok Imagine Video 1.5 supports native 1080p for text-to-video and image-to-video generation.
  • Reference-to-video generation with Grok Imagine Video 1.5 is capped at 720p.
  • The update fixes reference routing, addressing issues where non-image references were sent as empty arrays.
  • Grok Imagine Video 1.5 now supports referenceVoiceIds for reference audio in reference-to-video, allowing up to 3 xAI preset voice IDs.
  • The @ai-sdk/google@2.0.88 and @ai-sdk/google-vertex@3.0.163 releases introduce the gemini-3.7-flash model.

Context

According to the Vercel AI SDK changelog, the @ai-sdk/xai package now integrates Grok Imagine Video 1.5, expanding its video generation capabilities. The @ai-sdk/google and @ai-sdk/google-vertex packages have also been updated to include the Gemini 3.7 Flash model, as noted in their respective changelogs.

Why It Matters

These updates expand the range of models available through the Vercel AI SDK, offering developers new options for video generation and language model integration. The addition of 1080p video output for Grok Imagine Video 1.5 and the Gemini 3.7 Flash model provides enhanced capabilities for applications built with the SDK.

What To Do

  • Review the @ai-sdk/xai@3.0.121 changelog for details on Grok Imagine Video 1.5 integration.
  • Test Grok Imagine Video 1.5 for text-to-video and image-to-video generation, noting the 1080p resolution.
  • Explore the use of referenceVoiceIds for adding reference audio to Grok Imagine Video 1.5 reference-to-video generations.
  • Check the @ai-sdk/google@2.0.88 and @ai-sdk/google-vertex@3.0.163 changelogs for information on the Gemini 3.7 Flash model.

Keep Exploring

/atlas/**grok**-family /atlas/**gemini**-family /techniques/multimodal-grounding