# Grok-Imagine-Video-1.5-Preview Ranks Second on Artificial Analysis Video Leaderboard > xAI's model enters the image-to-video space with native audio support, posting an Elo rating of 1,111 behind only ByteDance Seedance 2.0 while carrying an API price of $8.40 per minute at 720p. *Published 2026-06-09 · By Marcus Vance* Grok-imagine-video-1.5-preview is an image-to-video model from xAI featuring native audio generation and API access at a rate of $8.40 per minute. The grok-imagine-video-1.5-preview model from xAI has achieved a second place ranking on the Image to Video with Audio leaderboard maintained by Artificial Analysis. This position places it behind only the Dreamina Seedance 2.0 from ByteDance which holds the top spot with an Elo rating of 1,194. The model's own Elo rating stands at 1,111 on this leaderboard. The ranking is determined through blind user votes in the Artificial Analysis Video Arena as stated in the source material from Artificial Analysis. This benchmark system allows for direct comparison between different AI video generation models from leading organizations such as xAI and ByteDance. The inclusion of audio in the evaluation category highlights the importance of multimodal output in current video AI systems. In the separate without audio category the model ranks third. The top position belongs to Dreamina Seedance 2.0 720p at an Elo rating of 1,344. The second place belongs to xAI's earlier grok-imagine-video at 1,327. grok-imagine-video-1.5-preview sits at 1,326. These figures come from the same Artificial Analysis leaderboard page. The close margin between the second and third positions indicates competitive performance even when audio is excluded from the evaluation. ## What are the detailed rankings for grok-imagine-video-1.5-preview on the Artificial Analysis leaderboard? The leaderboard evaluates models based on their ability to generate videos from images while incorporating audio elements where applicable. The inclusion of audio represents an important feature in the current generation of video AI models. grok-imagine-video-1.5-preview offers this capability natively according to the published details. Other entities active in the space include Alibaba with its HappyHorse-1.0 model and Google with Veo 3.1 though specific rankings for those offerings are not provided in the current snapshot. The focus of the reported data remains on the top three entries from ByteDance and xAI. Rankings on the Artificial Analysis Video Arena rely exclusively on blind user votes. This methodology reduces bias from brand recognition or prior expectations. The resulting Elo ratings provide a quantitative measure of relative model quality within the tested categories. The with-audio and without-audio leaderboards together give a fuller picture of each model's strengths and limitations. ## What is the pricing structure for accessing grok-imagine-video-1.5-preview? The grok-imagine-video-1.5-preview model is available via the xAI API at a cost of $8.40 per minute of generated video. This pricing applies to 720p resolution output. The rate is listed as $0.14 per second in the xAI documentation which equates to the per minute figure. Availability is immediate through the xAI API. A broader rollout across the Grok app and X platform is in progress according to information from Artificial Analysis. This pricing positions the model in a competitive segment of the market for video generation services. > Grok debuts grok-imagine-video-1.5-preview, achieving #2 in Image to Video (With Audio) in the Artificial Analysis Video Arena, behind only ByteDance's Seedance 2.0!Artificial Analysis, @ArtificialAnlys account ## What technical specifications define the current capabilities of the model? The model supports modalities of image and video. This model currently does not support text-to-video according to the xAI documentation. Output resolution is set at 720p. Durations are limited to up to 15 seconds at the present time. Rate limits stand at 60 requests per minute. These constraints define the immediate scope of practical use cases for the model. Comparison of Top Models on Artificial Analysis Image to Video LeaderboardModelElo with AudioElo without AudioPrice per MinuteDreamina Seedance 2.0 720p1,1941,344Not specifiedgrok-imagine-video-1.5-preview1,1111,326$8.40grok-imagine-videoNot listed1,327Not specified ## What features are listed in order of current availability? - The model supports image to video generation with native audio. - Output is delivered at 720p resolution. - Generation is limited to durations of up to 15 seconds. - Access occurs through the xAI API with a rate limit of 60 requests per minute. - A broader rollout to the Grok app and X platform remains in progress. ## What are the market and stakeholder implications of this model release? The release of grok-imagine-video-1.5-preview by xAI contributes to the ongoing development in the frontier models space for video generation. Stakeholders in the AI industry can now access a model with native audio at a defined price point. The ranking provides a benchmark for comparison with offerings from ByteDance and other companies. Developers and businesses evaluating video AI tools have an additional option through the xAI API. The availability signals xAI's continued expansion into multimodal capabilities. The specific Elo ratings allow for quantitative assessment of model performance in blind evaluations. Enterprise users may consider the per-minute pricing when budgeting for large-scale video generation projects. The native audio feature reduces the need for separate post-processing steps in some workflows. Competitive pressure from the number two ranking may influence development priorities at other organizations including Google and Alibaba. The data from Artificial Analysis offers an independent reference point for procurement decisions. ## What can be expected next for grok-imagine-video-1.5-preview and xAI video models? A broader rollout across the Grok app and X is in progress. The current limitations include support only for image to video with durations up to 15 seconds. Future updates may expand these capabilities based on the trajectory of similar models in the industry. The model is accessible now via the xAI API with rate limits set at 60 requests per minute. This infrastructure supports usage for various applications in content creation and other areas. Continued participation in external benchmarks such as the Artificial Analysis Video Arena will likely provide updated performance metrics over time. Integration with existing xAI products could increase accessibility for end users beyond API customers. The competitive Elo scores suggest room for iterative improvements that could close the gap with the current leader. Market participants will monitor subsequent releases for changes in pricing or supported modalities. ## Sources 1. [The top Image to Video models with audio by Elo rating are: 1. Dreamina Seedance 2.0 720p (Elo 1194), 2. grok-imagine-video-1.5-preview (Elo 1111), ... Without audio: 1. Dreamina Seedance 2.0 720p (Elo 1344), 2. grok-imagine-video (Elo 1327), 3. grok-imagine-video-1.5-preview (Elo 1326)](https://artificialanalysis.ai/video/leaderboard/image-to-video) 2. [Grok debuts grok-imagine-video-1.5-preview, achieving #2 in Image to Video (With Audio) in the Artificial Analysis Video Arena, behind only ByteDance's Seedance 2.0! ... grok-imagine-video-1.5-preview costs $8.40 per minute of generated video, and is available now via xAI's API...](https://x.com/ArtificialAnlys/status/2064076452899992041) 3. [Modalities: Image, Video. This model currently does not support text-to-video. ... 720p $0.14 [per second] ... Rate limits: Requests per minute 60](https://docs.x.ai/developers/models/grok-imagine-video-1.5-preview) --- Source: https://aiintelreport.com/frontier-models/grok-imagine-video-1-5-preview-ranks-second-on-artificial-analysis-video-leaderboard Index: https://aiintelreport.com/llms.txt · Full text: https://aiintelreport.com/llms-full.txt