Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
Google Veo 3.1 is the latest state-of-the-art generative video model designed to transform text and image prompts into high-fidelity cinematic visuals. Building upon its predecessors, Veo 3.1 features significant upgrades in prompt adherence, visual realism, and native audio generation, creating 8-second clips with synchronized sound effects and dialogue.
Google Veo 3.1 is the latest state-of-the-art generative video model designed to transform text and image prompts into high-fidelity cinematic visuals. Building upon its predecessors, Veo 3.1 features significant upgrades in prompt adherence, visual realism, and native audio generation, creating 8-second clips with synchronized sound effects and dialogue.
No video yet. Submit the form to generate video.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
veo-3-1-lite--text-to-video-4K videoGoogleresolution: 4k | Starter | 5per run | $0.023 | - | - |
veo-3-1-lite--image-to-video-1080p videoGoogleresolution: 1080p | Starter | 4per run | $0.018 | - | - |
veo-3-1-lite-image-to-video-720p videoGoogleresolution: 720p | Starter | 3.5per run | $0.016 | - | - |
Competitor pricing costs $4027.273/day more
ApiPass is 83.90% lower, estimated at Based on 1,000 videos/day
veo-3-1-lite--text-to-video-4K
resolution: 4k
ApiPass Price
$0.773
170 credits per run
Competitor Prices
Complete guide to using Veo 3.1
Generate cost-efficient AI videos from text prompts or from one to two guiding frames through the Kie.ai adapter used by apipass.
Within this adapter, google/veo-3-1-lite maps to the Kie.ai model name veo3_lite and is used for lightweight video generation workflows. The implementation supports standard text-to-video generation and a first-and-last-frame mode that accepts one or two reference images, while keeping the request surface smaller than the more feature-complete Veo Fast variant.
Use a prompt to generate a video directly. This is the default mode and does not require any reference images.
Provide one or two images in imageUrls to guide the shot. With two images, the adapter treats them as the opening and ending frames and asks the provider to generate the motion between them.
Veo 3.1 Lite is designed as Google's most cost-effective video generation model, empowering developers to build high-volume video applications at less than 50% of the cost of Veo 3.1 Fast.
Despite its highly accessible price point, Veo 3.1 Lite does not compromise on performance, delivering the exact same generation speed as Veo 3.1 Fast so developers can rapidly iterate and craft the perfect video without long wait times
Balancing practical utility with professional capabilities, the model fully supports both Text-to-Video and Image-to-Video generation, providing creators and developers with flexible starting points for their dynamic content workflows.
To accommodate diverse viewing platforms and application needs, Veo 3.1 Lite offers flexible framing options that include both landscape (16:9) and portrait (9:16) aspect ratios, while outputting crisp video at 720p and 1080p resolutions.
Developers have tailored control over their content length by being able to customize video durations to exactly 4 seconds, 6 seconds, or 8 seconds, ensuring that generation costs seamlessly adjust according to the specific needs of the application.
The integration flow mirrors the asynchronous behavior implemented in KieAdapter.
Choose google/veo-3-1-lite as the model and build a payload with prompt plus any optional Veo-specific parameters you need, such as generationType, imageUrls, aspect_ratio, seeds, enableTranslation, and watermark.
Send the request to the Veo generation endpoint. The adapter injects callBackUrl automatically and returns a taskId when the upstream provider accepts the task.
Track the task asynchronously through the query API or your callback endpoint. The adapter maps upstream states such as queuing, processing, success, and fail into the platform task states.
After success, consume resultUrls from the task result object. For completed jobs, the adapter attempts to upload upstream output files to the configured CDN and returns the CDN-backed URLs when available.
These suggestions are derived from the parameters and validation rules currently implemented in the adapter.
Use TEXT_2_VIDEO when you only have a prompt. Switch to FIRST_AND_LAST_FRAMES_2_VIDEO only when you are supplying one or two guiding images.
Stick to 16:9, 9:16, or Auto. Any other value is rewritten to 16:9 by the adapter, so unsupported ratios do not provide extra control.
For frame-guided generation, choose images with clear visual continuity. One image works as a visual anchor, while two images should define a plausible start and end state for the motion.
Veo 3.1 Lite is suitable for validating prompt ideas, rough story beats, and quick creative drafts before moving to a more expensive video model.
The built-in 9:16 aspect ratio option makes the model practical for short-form mobile-first concepts, product teasers, and creator content mockups.
The FIRST_AND_LAST_FRAMES_2_VIDEO mode can be used to test transitions between storyboard frames or key visual beats without building a full animation pipeline.
The document uses google/veo-3-1-lite externally and veo3_lite in the request examples because that is the exact mapping implemented by _get_kie_api_model_name.
REFERENCE_2_VIDEO is intentionally omitted from the selectable modes because check_params explicitly limits that mode to veo3_fast.
The create-task API section documents the ApiPass request shape, where the model stays at the top level and Veo parameters are nested under input.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Create a new Veo 3.1 Lite video generation task
The Veo endpoint uses the standard ApiPass request envelope. Keep model at the top level and place Veo generation parameters under input.
1{
2 "model": "google/veo-3-1-lite",
3 "callBackUrl": "string (optional)",
4 "input": {
5 "prompt": "string",
6 "imageUrls": [
7 "string"
8 ],
9 "generationType": "TEXT_2_VIDEO | FIRST_AND_LAST_FRAMES_2_VIDEO",
10 "aspect_ratio": "16:9 | 9:16 | Auto",
11 "seeds": 12345,
12 "enableTranslation": true,
13 "watermark": true
14 },
15 "channel": "auto"
16}modelRequiredstringThe ApiPass model identifier for Veo 3.1 Lite.
"google/veo-3-1-lite"
callBackUrlOptionalstringOptional callback URL for task completion notifications.
"https://your-domain.com/api/callback"
inputRequiredobjectContainer for Veo generation parameters.
{"prompt":"A simple white coffee cup on a wooden table, steam rising"}channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
Use this object for Veo generation parameters. Prompt and all Veo-specific options must be sent inside input.
promptRequiredstringThe generation prompt.
"A simple white coffee cup on a wooden table, steam rising."
imageUrlsOptionalarray(URL)Reference images for frame-guided generation. Required when generationType is FIRST_AND_LAST_FRAMES_2_VIDEO. One or two images are supported by the adapter documentation.
["https://example.com/frame-1.png", "https://example.com/frame-2.png"]
generationTypeOptionalstringGeneration mode. Lite supports TEXT_2_VIDEO and FIRST_AND_LAST_FRAMES_2_VIDEO in this document.
Available options:
"TEXT_2_VIDEO"
aspect_ratioOptionalstringOutput aspect ratio. The adapter defaults to 16:9.
Available options:
"16:9"
seedsOptionalnumberOptional seed value forwarded directly by the adapter.
12345
enableTranslationOptionalbooleanAutomatic prompt translation flag. Defaults to true when omitted.
true
watermarkOptionalbooleanOptional watermark flag. Only sent upstream when true.
true
durationOptionalstringThe duration of the generated video, in seconds. Optional values are 4, 6, 8.
Available options:
4
resolutionOptionalstringControls the pixel dimensions of the generated image. Higher resolution results in greater clarity and detail, while lower resolution allows for faster generation.
Available options:
720p
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "google/veo-3-1-lite",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "input": {
8 "seeds": 12345,
9 "prompt": "A simple white coffee cup on a wooden table, steam rising",
10 "imageUrls": [],
11 "watermark": false,
12 "aspect_ratio": "16:9",
13 "generationType": "TEXT_2_VIDEO",
14 "enableTranslation": true
15 }
16 }'1{
2 "code": 200,
3 "msg": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code. 200 indicates the task was created successfully.
msgResponse message from the provider.
data.taskIdTask identifier used for later status checks.
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Turn text, images, video clips, and audio into cinematic, audio-synced videos with a single API call.
Starting from
0 credits
MiniMax
MiniMax
Starting from
0 credits
ByteDance
ByteDance
Generate cinematic 4K AI videos up to 30 seconds with Seedance 2.5's multimodal power.
Starting from
0 credits
wan
wan
Starting from
0 credits
Runway
Runway
Starting from
0 credits
Kling
Kling
Transform text prompts and images into high-quality videos with advanced AI. Generate cinematic content with customizable duration, aspect ratio, and audio capabilities.
Starting from
0 credits
MiniMax
MiniMax
Generate high-quality AI videos from text prompts or images with MiniMax's Hailuo 2.3 model. Support for both 6s and 10s durations, 768p and 1080p resolutions, with intelligent prompt optimization.
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
Luma
Luma
Starting from
0 credits
Kling
Kling
Kling v3 video generation model, supports text-to-video and image-to-video, up to 15 seconds, 1080p pro mode
Starting from
0 credits
wan
wan
Generate videos with cinematic consistency by reimagining existing footage through high-fidelity visual transformation and structural control.
Starting from
0 credits
Starting from
0 credits
grok
grok
Starting from
0 credits
kling
kling
Starting from
0 credits