All Models

Lowest-cost Imagine video tier, added in October 2026, for 1-15 second text- or image-to-video with lip-synced audio. Reaches 1080p by upscaling 720p and lacks the reference, voice and keyframe controls of Video 1.5.

xAI's current recommended video model, generally available since June 16, 2026, for text-, image- and reference-to-video. Renders native 1080p clips up to 15 seconds with lip-synced audio, plus first, last and keyframe pinning and up to three preset voices.

FastVideo's 3-step quantization-aware distillation of Wan2.1-T2V-1.3B with FP8 layers (June 2026), producing 5-second 480p clips at 16 fps in a few seconds; trading visual detail for speed against larger Wan models.

Preview slug for Grok Imagine Video 1.5, announced June 3, 2026 as an image-to-video model up to 720p. The model left preview on June 16, and this name now resolves as an alias of grok-imagine-video-1.5.

Dated May 30, 2026 slug from the Grok Imagine Video 1.5 preview, which xAI now lists as an alias of grok-imagine-video-1.5. That preview build was image-to-video only at up to 720p; text-to-video and native 1080p came later.

Veo 3.1 Lite (veo-3.1-lite-generate-preview), launched March 31, 2026, is the lowest-cost Veo tier, generating video with native audio at 720p or 1080p but without 4K or extension. Gemini Omni Flash replaces it on October 22, 2026.

xAI's first Imagine video model (January 2026), producing 1-15 second clips up to 720p with generated audio. Superseded for generation by Grok Imagine Video 1.5, it remains xAI's only video model for editing and extending existing clips.

Veo 3.1 (veo-3.1-generate-preview), previewed in October 2025, makes 4- to 8-second clips with native audio at up to 4K, with reference images, frame control and extension. Gemini Omni Flash is its named replacement; shutdown is set for October 22, 2026.

Veo 3.1 Fast (veo-3.1-fast-generate-preview), the quicker, lower-priced Veo 3.1 tier from October 2025, keeps native audio, 4K output, reference images and video extension. Scheduled to shut down October 22, 2026 in favour of Gemini Omni Flash.

FastVideo (Hao AI Lab) 3-step DMD distillation of Wan2.2-TI2V-5B for text-to-video: 5-second, 24 fps clips at 720p or 480p in a few seconds. It runs without classifier-free guidance, so negative prompts have no effect.

Alibaba's open Wan2.2 text-to-video model (July 2025): a diffusion MoE with separate high-noise and low-noise experts (27B total, 14B active per step), served here for 5-second 720p clips. Its successor Wan 3.0 (August 2026) is not open-weight.