No. This endpoint supports image-to-video only. A prompt and at least one image source are required. The image source can be a reference image, first frame, last frame, loop image, or timed keyframe.
我们注意到您可能偏好使用 简体中文. 要切换语言吗？
Il semble que vous préfériez Français. Souhaitez-vous changer de langue ?
Es scheint, Sie bevorzugen Deutsch. Möchten Sie die Sprache wechseln?
Parece que prefieres Español. ¿Te gustaría cambiar de idioma?
Sembra che tu preferisca Italiano. Vuoi cambiare lingua?
優先言語は次のようです 日本語. 言語を切り替えますか？
선호하시는 언어는 다음과 같습니다 한국어. 언어를 변경하시겠습니까?
Похоже, вы предпочитаете Русский. Хотите сменить язык?
Tercih ettiğiniz dil Türkçe. Dili değiştirmek ister misiniz?
Wygląda na to, że wolisz Polski. Czy chcesz zmienić język?
Grok Imagine Video 1.5
Grok Imagine Video 1.5 animates reference images, first and last frames, timed keyframes, or a loop image through a single image-to-video API. Start at 24 Credits per second, choose 480p, 720p, or 1080p output, and direct clips from 1 to 15 seconds with prompts up to 5,000 characters.
Create with Grok Imagine Video 1.5
Capabilities
A focused image-to-video API with unusually accessible pricing
24 Credits Entry Rate
Use the 480p tier at 24 Credits per output second for inexpensive drafts, high-volume concept exploration, and short motion tests.
Seven-Image Guidance
Reference images guide appearance rather than acting as an ordered first and last frame pair. They can be omitted when another image source is supplied. The allowed reference count depends on resolution.
Three Resolution Tiers
Use a single first frame for higher-resolution output. Prefer the middle resolution tier when combining frame controls, and check input compatibility before generating.
Flexible Short Durations
Set any whole-second duration from 1 through 15 seconds instead of being limited to a small set of fixed clip lengths.
Six Frame Shapes
Keep automatic framing or request 1:1, 16:9, 9:16, 3:2, or 2:3 for square, landscape, portrait, and classic media layouts.
Detailed Motion Briefs
Use a required prompt from 1 to 5,000 characters to describe movement, camera behavior, pacing, subject actions, and scene intent.
Frame Controls
Direct endpoints, timing, and loops
First and last frames
Use dedicated frame inputs to define the opening and closing composition. Either endpoint can be supplied on its own; ordinary reference images are not an ordered frame pair.
Timed middle keyframes
Assign an explicit time in seconds to each middle frame. Decimal times are supported. Keep times inside the output duration and at least 1/3 second apart; shortening the clip requires checking the times again.
Loop image
Use a loop image for both opening and closing frames. It takes precedence over separate first and last frames while retaining reference images and timed keyframes. Prefer a compatible middle-tier resolution for loop workflows.
Model Details
Published Grok Imagine Video 1.5 API parameters
xAI
Provider
At Least One Image Source
Input
Video
Output
480p / 720p / 1080p
Resolution
1–15 Whole Seconds
Duration
Auto + 5 Ratios
Aspect Ratio
Use Cases
Where low-cost, multi-image video generation fits
Concept Exploration
Low-Cost Motion Drafts
Test several motion directions at 480p from 24 Credits per second before choosing which concept deserves a higher-resolution pass. The per-second formula keeps the cost of each draft easy to calculate.
Creative References
Multi-Image Visual Briefs
Reference images communicate visual appearance. Dedicated first and last frames define endpoints, while timed middle frames let you specify visual milestones at exact moments. Use a prompt to explain subject action, camera movement, and pacing between these controls.
Social Production
Landscape and Portrait Clips
Create short 16:9, 9:16, or square video concepts for different publishing surfaces, with 3:2 and 2:3 available when the source composition benefits from a photographic frame.
Resolution Planning
Draft-to-1080p Workflows
Explore timing and motion with a compatible frame-control workflow, then use a single first-frame image when requesting higher-resolution output. Combined frame controls are not universally available at every resolution. Review the final task status to distinguish accepted requests from successful generation.
Notes & FAQ
Grok Imagine Video 1.5 input and pricing guidance
Notes
01
Reference images, first and last frames, timed keyframes, and loop images use the same duration-and-resolution pricing.
02
Grok Imagine Video 1.5 supports image-to-video only. Supply a prompt and at least one reference image, first frame, last frame, loop image, or timed keyframe.
03
Reference-image limits depend on resolution. Timed keyframes use numeric times inside the clip, at least 1/3 second apart. Loop images override separate endpoints.
04
Duration must be a whole number from 1 to 15 seconds. Total price equals duration multiplied by the selected resolution rate.
05
Aspect ratio defaults to auto; explicit options are 1:1, 16:9, 9:16, 3:2, and 2:3.
06
The published APIXO rates per second are 24 Credits at 480p, 45 Credits at 720p, and 80 Credits at 1080p.
Frequently Asked Questions
The rate per second is 24 Credits at 480p, 45 Credits at 720p, and 80 Credits at 1080p. Multiply the chosen rate by the output duration to calculate the total price.
Reference-image limits depend on resolution and apply to that array independently of dedicated frames. Supply at least one image source; references are optional when a frame, loop image, or timed keyframe is present. Use a single first frame for the highest resolution and prefer the middle tier for combined frame controls.
Duration can be any whole number from 1 to 15 seconds. Aspect ratio can be auto, 1:1, 16:9, 9:16, 3:2, or 2:3, with auto used by default.
Yes. The APIXO API is available today. The in-browser workspace for this model is currently being wired up.
Explore Other Models
Discover more AI models for your next creative workflow
xai
Grok Imagine Video
Use xAI’s Grok Imagine Video API through APIXO for 6–30-second text-to-video and image-to-video generation with 480p, 720p, ratio, and style controls.
VideoNew
24 Credits/sec
VideoByteDance
Seedance 2.0
Use Seedance 2.0 API on APIXO for text, keyframe, and multimodal video generation with audio, mixed references, 4–15 second clips, and up to 4K output.
VideoNew
58 Credits/secAlibaba
HappyHorse
Use Alibaba HappyHorse through APIXO for text, first-frame, multi-reference, and video-edit workflows with audio and 720p or 1080p output.
VideoNew
125 Credits/secByteDance
Seedance 2.0 Fast
Generate 4–15 second Seedance 2.0 videos through APIXO using prompts, keyframes, mixed references, optional sound, and 480p or 720p output.
VideoNew
44 Credits/secByteDance
Seedance 2.5
Explore Seedance 2.5 for longer audiovisual storytelling, timeline direction, multimodal references, multilingual scenes, and selective video revision.
VideoNew
85 Credits/sec
MiniMax
MiniMax H3
Call MiniMax H3 through the APIXO API for 768p or 2K video with native stereo audio, from text, image, or mixed image/video/audio references. Text-to-video, image-to-video, and reference-to-video from one endpoint.
VideoNew
100 Credits/secByteDance
Seedance 1.5 Pro
Generate 4–12 second text- or image-led videos with Seedance 1.5 Pro on APIXO, including optional native audio and start-to-end frame control.
VideoNew
11 Credits/secGoogle
Gemini Omni
Use Gemini Omni on APIXO for multimodal video generation with image, source-video, reusable audio, and character references plus output up to 4K.
VideoNew
100 Credits/sec