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-extend-fast videoGooglemodel: fast | Starter | 5per run | $0.023 | Google Veo 3.1 Fast (8s extension)source$0.800per runGoogle charges per second; normalized to an 8-second extension. | Based on 1,000 videos/dayGoogle Veo 3.1 Fast (8s extension) costs $777.273/day moreApiPass is 97.16% lower |
veo-3-1-extend-quality videoGooglemodel: quality | Starter | 5per run | $0.023 | Google Veo 3.1 Standard (8s extension)source$3.200per runGoogle charges per second; normalized to an 8-second extension. | Based on 1,000 videos/dayGoogle Veo 3.1 Standard (8s extension) costs $3177.273/day moreApiPass is 99.29% lower |
veo-3-1-extend-lite videoGooglemodel: lite | Starter | 3.5per run | $0.016 | Google Veo 3.1 Lite (8s extension)source$0.400per runGoogle charges per second; normalized to an 8-second extension. | Based on 1,000 videos/dayGoogle Veo 3.1 Lite (8s extension) costs $384.091/day moreApiPass is 96.02% lower |
Competitor pricing costs $777.273/day more
ApiPass is 97.16% lower, estimated at Based on 1,000 videos/day
veo-3-1-extend-fast
model: fast
ApiPass Price
$0.023
5 credits per run
Competitor Prices
Complete guide to using Veo 3.1
Extend existing Veo 3.1 video generation tasks with natural continuation segments using the google/veo-3-1-extend API. Submit the original task ID, describe how the video should continue, choose fast, quality, or lite extension mode, and retrieve the finished video through the async task workflow.
Veo 3.1 Extend creates a new continuation segment from an existing Veo 3.1 video generation task. It is designed for clips that need to continue beyond their initial duration while keeping motion, scene logic, character appearance, and narrative flow coherent. The API accepts an original Veo 3.1 task ID and a prompt that describes the next action, scene transition, visual style, and continuity details. Only videos generated by Veo 3.1 can be extended, and 1080p source videos cannot be extended.
Create a new extension segment from a completed Veo 3.1 generation task. Pass the original taskId and describe what should happen next so the output continues the prior scene naturally.
Use text prompts to define action, style, camera behavior, scene changes, and continuity. English prompts are recommended for best results, and the prompt cannot be empty.
Choose fast, quality, or lite mode depending on your speed, quality, and credit requirements. The default mode is fast, with regular-channel pricing based on the selected mode.
Generate a continuation segment when your source clip needs more time to complete an action, reveal a story beat, or carry forward a scene. Veo 3.1 Extend helps the next segment feel connected to the original video instead of starting from scratch.
Describe how the next scene should connect, including character motion, environment, camera movement, and visual tone. This makes the API useful for character scenes, product shots, social clips, and cinematic sequences that need consistent flow.
Submit a task through /api/v1/jobs/createTask, store the returned data.taskId, and poll /api/v1/jobs/recordInfo until the state is success or fail. When successful, parse data.resultJson to retrieve the extended video URL.
Extend short Veo 3.1 clips into longer sequences for narrative videos, cinematic scenes, creator content, and social posts that need a second beat after the original generation.
Continue product, lifestyle, or promotional videos with new action while preserving the visual direction of the original clip. Use fast mode for rapid iteration and quality mode when output detail matters more.
Build workflows where a character, camera movement, or environment continues into a new segment. Prompt for consistent appearance, lighting, motion, and scene rhythm to support multi-part video experiences.
Choose the extension mode that fits your production tradeoff between speed, quality, and credit cost.
fast is the default extension mode. It is suited for quick continuation tasks, draft iterations, and workflows where turnaround speed matters. On the regular channel, fast costs 70 credits per video task.
quality is intended for higher-detail continuation tasks where smoother motion, richer visual consistency, and final output quality are more important than credit cost. On the regular channel, quality costs 279 credits per video task.
lite is the lowest-cost extension mode for lighter workloads, previews, and budget-sensitive testing. On the regular channel, lite costs 37 credits per video task.
On the regular channel, pricing depends on the selected extension mode: fast costs 70 credits, quality costs 279 credits, and lite costs 37 credits per video task.
Use channel auto to let ApiPass allocate tasks across available providers based on pricing and stability. You can also select starter, regular, or official when your workflow needs a specific channel behavior.
Each extension request creates an independent video task. Save the returned data.taskId and query the task status until completion before reading the generated URL from data.resultJson.
Start with a completed Veo 3.1 video generation task. Pass the ApiPass task_* ID or the source task ID directly as input.taskId. The source must be a Veo 3.1 generated video, and 1080p source videos cannot be extended.
Write an English prompt that explains how the video should continue. Include the next action, scene transition, camera movement, style, lighting, and continuity details so the extension connects naturally to the existing clip.
Send a POST request to /api/v1/jobs/createTask with model google/veo-3-1-extend, then store the returned data.taskId. Poll /api/v1/jobs/recordInfo until the state is success or fail. On success, parse data.resultJson to access the extended video URL.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Submit a new Veo 3.1 video extension task based on an existing Veo 3.1 generation task.
The API accepts a JSON payload with the following structure:
1{
2 "model": "google/veo-3-1-extend",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "taskId": "string",
7 "prompt": "string",
8 "model": "fast",
9 "seeds": 12345,
10 "watermark": "string (optional)"
11 }
12}modelRequiredstringThe model name to use for the video extension task. This must be fixed as google/veo-3-1-extend.
"google/veo-3-1-extend"
callBackUrlOptionalstringOptional client callback URL for task completion notifications. The source API does not require clients to pass callBackUrl because ApiPass uses a system callback address internally; clients can poll task status instead.
"https://your-domain.com/api/callback"
channelOptionalstringSelect the provider channel within APIPASS. The default channel is auto, where APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. starter is ultra-low-cost with limited quotas and weaker stability; regular is standard and much cheaper than official APIs with moderate stability; official uses the model native API with high stability, fast task execution, and official pricing.
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. starter is ultra-low-cost with limited quotas and weaker stability; regular is standard and much cheaper than official APIs with moderate stability; official uses the model native API with high stability, fast task execution, and official pricing.
Available options:
auto
The input object contains the following parameters:
input.taskIdRequiredstringThe task ID of the original Veo 3.1 video generation task. You can pass an ApiPass task_* ID, which ApiPass resolves to the corresponding apipass task ID, or pass a apipass task ID directly. The source task must be a Veo 3.1 generated video, and 1080p source videos cannot be extended.
"veo_task_abcdef123456"
input.promptRequiredstringText prompt describing the action, scene, style, and transition behavior for the extended video segment. The prompt cannot be empty.
Use English for best results. Describe how the continuation should connect to the existing video, including action, scene, style, motion, and continuity details.
"The dog continues running through the park, jumping over obstacles and playing with other dogs"
input.modelOptionalstringapipass extension mode. Defaults to fast. Pricing on the regular channel depends on this mode: fast = 70 credits, quality = 279 credits, lite = 37 credits per video task.
Available options:
"fast"
input.seedsOptionalintegerRandom seed used for generation. Valid range is 10000 to 99999. Numeric strings such as "12345" are converted to integers. If omitted, a seed is generated automatically.
12345
input.watermarkOptionalstringWatermark text to add to the output video.
"ApiPass"
1curl --request POST \
2 --url "https://api.apipass.dev/api/v1/jobs/createTask" \
3 --header "Authorization: Bearer ${APIPASS_API_KEY}" \
4 --header "Content-Type: application/json" \
5 --data '{
6 "model": "google/veo-3-1-extend",
7 "channel": "auto",
8 "input": {
9 "taskId": "veo_task_abcdef123456",
10 "prompt": "The dog continues running through the park, jumping over obstacles and playing with other dogs",
11 "model": "fast",
12 "seeds": 12345
13 }
14 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code, 200 for success, others for failure.
messageResponse message. When the request fails, this contains the error description.
data.taskIdApiPass task ID for querying the video extension task status and result.
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
topaz
topaz
Topaz Video Upscaler API delivers professional-grade AI video enhancement, restoring detail, reducing noise, and providing high-quality upscaling to 1080p or 4K.
Starting from
0 credits
Luma
Luma
Starting from
0 credits
Starting from
0 credits