Veo 3.1

Video with AudioReference GuidedUp to 4K

Veo 3.1 on APIXO packages Google’s Lite, Fast, and standard Veo 3.1 generation tiers behind one route. Create short videos from text, ordered first-and-last frames, or up to three visual references, with native audio, portrait or landscape framing, and APIXO output options from 720p through 4K.

Workflows

Text / Frames / References

APIXO Price

$0.15–$2.40 / Video

Resolution

720p / 1080p / 4K

Duration

4 / 6 / 8 Seconds

Framing

16:9 / 9:16 / Auto

Loading workspace...

Capabilities

Creative control across image, motion, camera, and sound

Native Audiovisual Generation

Veo 3.1 generates sound with the video, allowing prompts to describe dialogue, ambience, music, and effects. APIXO exposes no audio-disable or uploaded-audio field.

Directed Camera Language

Prompts can specify shot composition, lens perspective, camera movement, pacing, lighting, action, and atmosphere for more intentional short-form visual storytelling.

First-to-Last Transitions

Supply an opening image and optionally an ending image to guide the transition between two defined visual states. Image order determines the start and end roles.

Multi-Image Guidance

APIXO’s reference workflow accepts one to three public images as visual guidance for subjects, products, characters, and scene content. The images provide general conditioning rather than guaranteed identity, geometry, branding, or formal style-reference control.

Portrait Video Creation

Generate landscape or portrait clips for campaign, mobile, and social layouts. APIXO also provides auto framing when a fixed ratio is unnecessary.

Seed-Controlled Iteration

An optional seed can improve consistency between comparable attempts, but it does not guarantee deterministic reproduction when prompts, references, routing, or provider behavior change.

Image-Guided Workflows

Choose endpoint frames or broader visual references

First-and-Last-Frame Video

Use FIRST_AND_LAST_FRAMES_2_VIDEO with one starting image or an ordered start-and-end pair. APIXO accepts up to two URLs and exposes lite, fast, or quality routing for this transition-focused workflow.

Up to 2 Frames

Reference-Guided Video

Use `REFERENCE_2_VIDEO` with one to three images as subject and visual-content guidance. APIXO requires `fast` mode and an 8-second duration; references remain conditioning inputs rather than fixed frames or dedicated style-reference controls.

1–3 References

Veo 3.1 Extend

Continue a completed Veo 3.1 task through the separate veo-3-1-extend route. Extension uses the previous task ID plus a new prompt and supports fast or quality continuation pricing.

$0.20-$1.50 / Video

API Details

Veo 3.1 route specifications

Verified controls and outputs exposed by APIXO’s main generation route.

Lite / Fast / Quality

Modes

1–10,000 Characters

Prompt

3 Generation Types

Workflows

Up to 3 Public URLs

Image Inputs

1 MP4 Video URL

Output

Polling / Callback

Delivery

Use Cases

Production workflows suited to Veo 3.1

Campaign Creative

Product and Brand Videos

Generate short product reveals, campaign concepts, and ecommerce scenes with directed camera movement and native sound. Review product proportions, logos, embedded text, and reference fidelity before publishing.

Mobile Media

Portrait Social Clips

Create 9:16 audiovisual scenes for mobile placements without reframing a landscape master. Validate spoken wording, pronunciation, lip synchronization, anatomy, and rapid motion during editorial review.

Controlled Transitions

Animate Between Keyframes

Define an opening state and optional ending state for transformation shots, visual transitions, or storyboard beats. Complex object contact and large changes between frames may require several attempts.

Previsualization

Reference-Guided Shot Concepts

Combine character, product, wardrobe, or scene references with camera and action instructions to explore a proposed shot. Treat references as guidance rather than guarantees of exact identity or design.

Notes & FAQ

Compatibility and operational guidance

Integration Notes

APIXO exposes `lite`, `fast`, and `quality` route modes. Google separately documents Veo 3.1 Lite, Veo 3.1 Fast, and standard Veo 3.1, but APIXO does not publicly identify the exact upstream model ID selected for each route mode.

Google requires an 8-second duration for 1080p, 4K, reference-image generation, and first-to-last-frame interpolation. APIXO exposes 4, 6, and 8 seconds through its general schema, so applications should validate workflow-specific combinations before submitting production tasks.

Google documents 8-second output as required for 1080p, 4K, and reference-image generation; use 8 seconds even though APIXO’s general selector exposes 4, 6, and 8.

APIXO lists a 4K Lite option, while Google’s current Veo 3.1 Lite documentation states that Lite does not support 4K; confirm the active route before production use.

Typical generation takes 1–3 minutes; APIXO recommends first polling after 60–90 seconds for Lite or Fast and after 90 seconds for Quality, then every 5–10 seconds.

APIXO handles video continuation through the separate `veo-3-1-extend` route. Extension requires a completed task ID returned by the main Veo 3.1 route and supports separate `fast` or `quality` continuation modes.

Frequently Asked Questions

Pricing is per generated video, determined by mode and resolution—not duration. Lite costs $0.15, $0.25, or $0.75; Fast costs $0.30, $0.375, or $0.90; Quality costs $1.60, $1.80, or $2.40 for 720p, 1080p, or 4K respectively.

Google documents native audio as always enabled across the Veo 3.1 family. Prompts can request dialogue, ambience, music, and effects, but APIXO exposes no sound toggle, uploaded-audio conditioning, voice selector, pronunciation field, or lip-sync control.

APIXO recommends directly reachable public JPG, JPEG, or PNG URLs up to 10 MB. WebP is not documented. URLs should remain accessible throughout processing so the selected route can retrieve each image.

No. APIXO’s watermark field adds optional user-provided text to the generated video. It is not a watermark-removal control and does not remove Google SynthID or other provenance and safety mechanisms.

The route documents no negative prompt, prompt-enhancement switch, person-generation setting, output-count control, safety-level field, audio setting, FPS selector, or camera preset. Google’s direct API options should not be assumed available through APIXO.

Explore Other Models

Discover more AI models for your next creative workflow

View all models

OpenAI

Sora 2 Pro

Sora 2 Pro is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.3/sec

OpenAI

Sora 2

Sora 2 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

Video

$0.1/sec

ByteDance

Seedance 2.0

Seedance 2.0 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.0573/sec

Google

Gemini Omni

Gemini Omni is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.1/sec

Alibaba

HappyHorse

HappyHorse is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.125/sec

ByteDance

Seedance 2.0 Fast

Seedance 2.0 Fast is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.044/sec

ByteDance