Use the Grok Imagine Video 1.5 API for text-to-video, image-to-video with optional last frame, and reference-to-video with up to seven images. Generate 1–15 second clips with native audio in 480p, 720p, or 1080p, or pick Grok Imagine Video 1.5 Lite for the lowest per-second cost.
Grok Imagine Video 1.5 Grok Imagine Video 1.5 Text to Video is a live Muapi endpoint for text-to-video. Submit it with one API key and poll the shared result endpoint.
Grok Imagine Video 1.5 Grok Imagine Video 1.5 Image to Video is a live Muapi endpoint for image-to-video. Submit it with one API key and poll the shared result endpoint.
Grok Imagine Video 1.5 Grok Imagine Video 1.5 Reference to Video is a live Muapi endpoint for image-to-video. Submit it with one API key and poll the shared result endpoint.
Grok Imagine Video 1.5 Lite Grok Imagine Video 1.5 Lite Text to Video is a live Muapi endpoint for text-to-video. Submit it with one API key and poll the shared result endpoint.
Grok Imagine Video 1.5 Lite Grok Imagine Video 1.5 Lite Image to Video is a live Muapi endpoint for image-to-video. Submit it with one API key and poll the shared result endpoint.
Grok Imagine Video 1.5 Preview Grok Imagine Video 1.5 Preview is a live Muapi endpoint for image-to-video. Submit it with one API key and poll the shared result endpoint.
The Grok Imagine Video 1.5 API gives developers xAI's video model through one asynchronous endpoint catalog. Generate clips from a text prompt, animate a still image with an optional last frame, or guide a video with up to seven reference images. Every clip can include a synchronized native audio track, runs from 1 to 15 seconds, and supports nine aspect ratios from 16:9 and 9:16 to 21:9 and 5:2.
Choose Grok Imagine Video 1.5 for 480p, 720p, or 1080p output, or Grok Imagine Video 1.5 Lite when cost matters most. Lite costs 25% of the standard rate and supports text-to-video and single-image video. Both use the same Muapi API key, request ID, result polling endpoint, and optional webhook as the rest of the [Grok Imagine API](/grok-imagine).
Turn a prompt into a 1–15 second clip with native audio, nine aspect ratios, and 480p, 720p, or 1080p output.
Animate one image as the first frame, or add a last frame to control where the clip ends (480p and 720p with a last frame).
Guide identity and style with one to seven reference images. Available on Grok Imagine Video 1.5 at 480p and 720p.
Grok Imagine Video 1.5 Lite delivers text and image to video at 25% of the standard per-second price.
Submit a Grok Imagine Video 1.5 task with JSON, save the request ID, and poll the standard result endpoint.
curl -X POST https://api.muapi.ai/api/v1/grok-imagine-video-1-5-text-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A dog running on a sunny beach, cinematic slow motion","aspect_ratio":"16:9","duration":8,"resolution":"720p","generate_audio":true}'
# Response: {"request_id":"REQUEST_ID"}Set aspect ratio, duration, resolution, and whether to generate audio.
curl -X POST https://api.muapi.ai/api/v1/grok-imagine-video-1-5-image-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"The camera slowly pushes in as the subject smiles","image_url":"https://example.com/photo.jpg","duration":8,"resolution":"720p"}'Provide a first-frame image URL and optionally a last_image URL.
curl -X POST https://api.muapi.ai/api/v1/grok-imagine-video-1-5-reference-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"The character from the references walks through a neon city at night","images_list":["https://example.com/ref1.jpg","https://example.com/ref2.jpg"],"aspect_ratio":"16:9","duration":8,"resolution":"720p"}'Provide a prompt and one to seven reference image URLs.
curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \ -H "x-api-key: YOUR_API_KEY"
Read the completed video URL from the outputs array.
It is an asynchronous API for xAI's Grok Imagine Video 1.5 model. It generates videos from text, from an image, or from multiple reference images, with optional native audio.
Grok Imagine Video 1.5 costs $0.08 per second at 480p, $0.14 per second at 720p, and $0.25 per second at 1080p. An 8-second 480p clip costs $0.64.
Lite costs 25% of the standard rate: $0.02 per second at 480p, $0.035 per second at 720p, and $0.0625 per second at 1080p.
Choose 480p, 720p, or 1080p and any duration from 1 to 15 seconds. 1080p is generated by upscaling 720p. Reference-to-video supports 480p and 720p.
Yes. `generate_audio` defaults to true and adds a synchronized audio track. Set it to false for a silent video.
No. Lite supports text-to-video and single-image image-to-video. Use Grok Imagine Video 1.5 for reference-to-video with up to seven images.
Use one API key to generate videos with Grok Imagine Video 1.5 and 1.5 Lite from text, images, or references.