Grok Imagine Video 1.5
Released Jun 16, 2026
xAI's video generation model, generally available on the Imagine API, generating video with sound effects, ambience and lip-synced dialogue in a single pass.
- Price per second
- $0.080
- Max clip length
- 15 s
- Max resolution
- 1080p
- Native audio
- Yes
- AA arena Elo
- 1057
- LMArena Elo
- 1492
- Capabilities
- text to video, image to video
- Licence
- Proprietary
Strengths & weaknesses
Strengths
- Native 1080p for text-to-video and image-to-video
- Single-pass audio with lip-synced speech
- Up to 15-second clips with first, last and mid-video keyframes
- Reference-to-video with preset voices for up to 3 speakers
Weaknesses
- No video editing or extension (the older grok-imagine-video model still handles those)
- Reference-to-video limited to 720p
releaseDate is the GA post on x.ai (June 16 2026); a grok-imagine-video-1.5-preview preceded it per third-party listings only. The launch post describes it as image-to-video; text-to-video and reference-to-video were added in July 2026 per xAI's API release notes. Lite release date not found on an xAI page (third-party listings disagree: Oct 1 vs Oct 8 2026). Leaderboards: LMArena entry is 'grok-imagine-video-1.5-agent' (#4, preliminary, Sep 21 2026), an agent configuration rather than the plain API model, and the leaderboard lists the creator as 'SpaceXAI'; company kept as xai. Artificial Analysis: Grok Imagine Video 1.5 1057 (#12, AA-Video-T2V v2.1, 2026-10-27); Grok Imagine Video 1.5 Lite 990.
Links
API model strings
- xai
grok-imagine-video-1.5 - xai
grok-imagine-video-1.5-lite