Use a prompt on its own, or add a start frame and an optional end frame. Select 720p, 1080p, or 4K output and a length of 4, 6, or 8 seconds. Review the picture, movement, and sound before using the clip.
The final cost is rounded up to whole credits.

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

Example output
Veo3.1 Quality
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
Credit charges
Credit rate: 225–285 per video
Inputs
Prompt + optional images
Prompt requirements
Up to 5,000 characters
Developer access
Veo3.1 Quality 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 Quality FAQ
No. You can submit a prompt without images. For frame input, add a starting image or a starting and ending pair, with up to 2 images in total. Use JPEG or PNG files no larger than 10 MiB each. The separate reference image mode is not supported by this model.
Use Rivya's upload flow so the images carry the required metadata. Generation checks that metadata against the image URL, your account, and this model. A pasted URL by itself does not meet those checks. Only upload images you have permission to use.
Extend needs a successful original Veo3.1 Quality task in your account. A 1080p or 4K result request needs a successful 720p original task or a successful Quality Extend result. Direct 1080p and 4K clips, and earlier resolution-action results, cannot be used for another resolution request. Each action creates its own task and reserves credits separately.
Initial generation reserves 225 credits for 720p, 233 for 1080p, or 285 for 4K. The 1080p reservation rounds up from 232.5 credits. Extend reserves 225 credits; eligible 1080p and 4K result requests reserve 8 and 60 extra credits respectively. A ready video does not confirm the final charge. An interrupted request does not prove failure or a refund.
Judge the returned clip against your brief, including its motion, details, and sound. If you are comparing models, use the same scene and check each model's inputs and credit estimate. An audio track is not guaranteed, and this form has no separate audio controls. Review the clip yourself before sharing it with a client.
Write what happens in the scene and how the camera should move. Leave images out for text input, or upload a start frame and an optional end frame. Check the output settings and estimate before submitting.
Set the aspect ratio, resolution, and clip length. You can also add watermark text or allow automatic prompt translation to English. The form offers 720p, 1080p, or 4K output and clip lengths of 4, 6, or 8 seconds.
Check the subject, movement, framing, and any sound against what you asked for. Look for visual errors, and confirm that you have permission to use your inputs. Keep a copy of a result you want to use; a preview is not a promise that its remote URL will stay available.
Sign in before submitting. Rivya reserves the estimate before sending the provider request. Valid reported usage within the reservation sets the final charge, and any unused reserved credits are returned. Missing, invalid, or higher usage leaves the final charge unconfirmed. If a request is interrupted, check the existing task in History before retrying.
This page keeps Veo3.1 Quality selected. Studio lets you choose other models and media. Submitted generation tasks appear in your account's History. Opening Studio does not submit a request or guarantee that all settings from a previous task will carry over.
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