Choose 720p, 1080p, or 4K output and a clip length of 4, 6, or 8 seconds. For reference-image input, use 8-second clips with an aspect ratio of 16:9 or 9:16. Check the selected mode before submitting.
The final cost is rounded up to whole credits.

Example output
Veo3.1 Lite
Text to Video · Image to Video

Example output
Veo3.1 Lite
Best for
Supports
Try this model
No results to display yet.
Model examples
Review examples to help decide whether the model fits your task.
Model strengths
Model strengths
Suggested uses
Tasks to consider
Model details
Provider
Category
Video
Capabilities
Text to Video · Image to Video · Reference to Video
Credit charges
Credit rate: 15–75 per video
Inputs
Prompt + optional images
Prompt requirements
Up to 5,000 characters
Developer access
Veo3.1 Lite can be called through Public API v1. Modes that use reference media require uploads through the Files API. Check the model reference for supported inputs.
Veo3.1 Lite FAQ
In frame mode, upload a starting image and add an ending image if needed. Reference mode accepts one to 3 images to guide the clip rather than define its endpoints. That mode requires 8 seconds and an aspect ratio of 16:9 or 9:16.
Use JPEG or PNG images no larger than 10 MiB each. Upload through Rivya so the required metadata is checked against your account, this model, and the image URL. A URL without that metadata is not enough. Only use images you have permission to upload.
Extend is available for a successful original Lite task in your account. For a 1080p or 4K result action, the source must be a successful 720p original task or a successful Lite Extend result. Direct 1080p and 4K clips and earlier resolution-action results do not qualify for another resolution action. Each action is a new task with its own credit reservation.
A new clip reserves 15 credits for 720p, 23 for 1080p, or 75 for 4K. The 1080p amount is rounded up from 22.5. Extend reserves 15; eligible 1080p and 4K result actions reserve another 8 and 60 credits respectively. A completed clip can still have an unconfirmed final charge.
Keep the scene and output settings as similar as the models allow, then inspect the returned clips and their credit estimates. Model names alone do not guarantee better motion, detail, or sound. Audio can be missing, and this form has no separate audio control. Review the result before using it.
Yes. Write a prompt and leave the image input empty for text-to-video generation. To use images, choose frames or reference images and check that mode's limits. Adding files does not submit a generation by itself.
The form offers 720p, 1080p, or 4K and clip lengths of 4, 6, or 8 seconds. Reference-image mode requires 8 seconds and 16:9 or 9:16; Auto is not available in that mode. You can also add watermark text or enable prompt translation to English.
Check the prompt, image order, generation mode, and output settings. Read the credit estimate and make sure you have permission to use the inputs. The first image is the start frame in frame mode; reference-image mode uses the files as guidance instead.
Sign in before uploading or submitting a generation. Rivya reserves the estimate before sending the provider request. Valid reported usage within that reservation confirms the final charge and returns any unused credits. Missing, invalid, or higher usage leaves settlement unconfirmed. If the request is interrupted, check its task in History before sending another one; an interruption does not prove that generation failed.
Yes. This page keeps Lite selected, while Studio lets you choose models across its media categories. Both use the same generation controls for Lite. Submitted tasks are saved in your account's History. Opening Studio does not start another generation or restore every input from a previous task.
Compare alternatives
Create Seedance 2.5 videos from text, a start frame with an optional end frame, or image, video, and audio references. Choose 480p, 720p, or 1080p, a duration from 4 to 30 seconds or automatic duration, and an MP4 or MOV format request.
Why consider it
Input option: Up to 50 reference files
Generate video from text, a first frame, or media references.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references
ByteDance's Seedance 2.0 Fast video model for text prompts, a first frame with an optional last frame, or image, video and audio references. Choose 480p or 720p, set a 4–15-second duration, and request audio or a returned last frame.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references