API Stock

AI video generation API

Choose a video generation API for prompt-based clips, image animation or audio-enabled video. Compare current model prices, input requirements and output options through one API key.

Models available

Start with the asset your application already has: a written brief, a product image or reference footage. That determines which API workflow fits. Then compare supported clip lengths, output formats and total cost for the same deliverable. A low per-second rate alone does not tell you the price of a finished clip.

Choose for your task

A new shot from a written brief

For storyboards, ad concepts and scene drafts, shortlist text-to-video routes that accept a prompt without mandatory media. Compare subject consistency and camera movement using the same brief.

Check available duration and aspect ratio first. Generate a short draft before paying for higher resolution; a model name containing Fast does not guarantee a queue time.

Models to evaluate

Animate an existing product or key visual

For a product card, hero loop or social ad, start from an approved image. Compare how each route preserves the product, framing and background while adding the requested motion.

Image-to-video support does not imply support for a last frame, several references or motion control. Check the actual image fields and required inputs on the model page.

Models to evaluate

A clip with sound

If dialogue or ambience belongs in the deliverable, evaluate routes with an explicit audio-generation control. Compare the complete clip with sound enabled, rather than a silent starting tariff.

An audio switch is a schema capability, not a guarantee of dialogue accuracy or lip sync. Test your language and script. Some other models include sound without exposing this switch.

Models to evaluate

Models and current API prices

Starting prices come from the live catalog and refer to each model’s cheapest published tier. Per-second rates and whole-generation prices buy different amounts of output. Compare the same duration, resolution and audio settings on the model page. Options below are individual schema values; not every combination is supported.

Model	Starting price	Inputs and controls	Declared options	All prices and parameters
Agnes Video 2.5	From $0.023per second	text-to-video image-to-video `imageUrls` `audioUrls`	`aspectRatio`: 16:9 \| 9:16 \| 21:9 \| 4:3 +2 `resolution`: 720p \| 1080p \| 2k `duration`: 1–12	All prices and parameters
FLUX 3 Video	From $0.06per second	text-to-video image-to-video `imageUrls` `videoUrl`	`resolution`: 720p \| 1080p `duration`: 5–20 `aspectRatio`: auto \| 21:9 \| 2:1 \| 16:9 +4	All prices and parameters
Gemini Omni 1.1 Flash	From $0.279per generation	text-to-video image-to-video `imageUrls` `referenceImageUrls` `referenceVideoUrls`	`aspectRatio`: 16:9 \| 9:16 `duration`: 4 \| 6 \| 8 \| 10 `resolution`: 360p \| 720p \| 1080p \| 4k	All prices and parameters
Grok Imagine 1.5 Video	From $0.015per second	text-to-video image-to-video `urls`	`size`: 16:9 \| 9:16 \| 1:1 \| 3:2 +1 `duration`: 6 \| 10 \| 15 \| 20 +2 `resolution`: 480p \| 720p	All prices and parameters
Kling 3.0	From $0.096per second	text-to-video image-to-video `generateAudio` `imageUrls`	`resolution`: 720p \| 1080p \| 4k `duration`: 3–15 `aspectRatio`: 16:9 \| 9:16 \| 1:1	All prices and parameters
Kling 3.0 Motion Control	From $0.065per second	text-to-video image-to-video `imageUrls` · Required `videoUrls` · Required	`resolution`: 720p \| 1080p	All prices and parameters
Kling 4.0	From $0.171per second	text-to-video image-to-video `generateAudio` `imageUrls` `startFrameUrl` `keyframeUrls` `endFrameUrl` `videoUrl`	`resolution`: 720p \| 1080p `duration`: 3–30 `aspectRatio`: auto \| 16:9 \| 9:16 \| 1:1 +1	All prices and parameters
MiniMax H3	From $0.016per second	text-to-video image-to-video `imageUrls` `audioUrls`	`aspectRatio`: 16:9 \| 9:16 `resolution`: 480p \| 768p \| 1080p `duration`: 1–15	All prices and parameters
PixVerse V6	From $0.024per generation	text-to-video image-to-video `imageUrls` `firstFrameImage` `lastFrameImage`	`resolution`: 360p \| 540p \| 720p \| 1080p `duration`: number `size`: 16:9 \| 4:3 \| 1:1 \| 3:4 +4	All prices and parameters
Seedance 1.5 Pro	From $0.065per generation	text-to-video image-to-video `generateAudio` `imageUrls`	`duration`: 4 \| 8 \| 12 `size`: 16:9 \| 9:16 \| 1:1 \| 4:3 +2 `resolution`: 480p \| 720p \| 1080p	All prices and parameters
Seedance 2.0	From $0.091per second	text-to-video image-to-video `generateAudio` `imageUrls` `videoUrls` `audioUrls`	`duration`: 4–15 `size`: adaptive \| 16:9 \| 9:16 \| 1:1 +3 `resolution`: 480p \| 720p \| 1080p \| 4k	All prices and parameters
Seedance 2.0 Fast	From $0.057per second	text-to-video image-to-video `generateAudio` `imageUrls` `videoUrls` `audioUrls`	`duration`: 4–15 `size`: adaptive \| 16:9 \| 9:16 \| 1:1 +3 `resolution`: 480p \| 720p	All prices and parameters
Seedance 2.0 Mini	From $0.023per second	text-to-video image-to-video `generateAudio` `imageUrls` `videoUrls` `audioUrls`	`duration`: 4–15 `size`: adaptive \| 16:9 \| 9:16 \| 1:1 +3 `resolution`: 480p \| 720p	All prices and parameters
Seedance 2.5	From $0.137per second	text-to-video image-to-video `generateAudio` `imageUrls` `videoUrls` `audioUrls`	`duration`: 4–30 `size`: adaptive \| 16:9 \| 4:3 \| 1:1 +3 `resolution`: 480p \| 720p \| 1080p	All prices and parameters
Seedance 2.5 Spicy	From $0.143per second	text-to-video image-to-video `generateAudio` `imageUrls` `videoUrls` `audioUrls`	`duration`: 4–30 `size`: adaptive \| 16:9 \| 4:3 \| 1:1 +3 `resolution`: 480p \| 720p \| 1080p	All prices and parameters
Veo 3.1 Fast	From $0.2per generation	text-to-video image-to-video `urls`	`aspectRatio`: 16:9 \| 9:16 `resolution`: 720p \| 1080p \| 4k	All prices and parameters
Veo 3.1 Lite	From $0.1per generation	text-to-video	`aspectRatio`: 16:9 \| 9:16 `resolution`: 720p \| 1080p \| 4k	All prices and parameters
Veo 3.1 Quality	From $1.43per generation	text-to-video image-to-video `urls`	`aspectRatio`: 16:9 \| 9:16 `resolution`: 720p \| 1080p \| 4k	All prices and parameters
Wan 2.7 Video	From $0.086per second	text-to-video image-to-video `imageUrls` `referenceImageUrls` `referenceVideoUrls` `editVideoUrl` `referenceImageUrl` `continueVideoUrl` `audioUrl`	`size`: 16:9 \| 9:16 \| 1:1 \| 4:3 +1 `resolution`: 720p \| 1080p `duration`: number	All prices and parameters
Wan 3.0 Pro	From $0.086per second	text-to-video image-to-video `imageUrls` `videoUrls` `audioUrls` `fileUrl` `linkUrl`	`size`: adaptive \| 16:9 \| 4:3 \| 1:1 +2 `duration`: 2–30 `resolution`: 480p \| 720p \| 1080p \| 2K +1	All prices and parameters
Wan 3.0 Video	From $0.047per second	text-to-video image-to-video `imageUrls` `videoUrls` `audioUrls` `fileUrl` `linkUrl`	`size`: adaptive \| 16:9 \| 4:3 \| 1:1 +2 `resolution`: 480p \| 720p \| 1080p `duration`: 2–30	All prices and parameters
Wan 3.0 Video Prime	From $0.066per second	text-to-video image-to-video `imageUrls` `videoUrls` `audioUrls` `fileUrl` `linkUrl`	`size`: adaptive \| 16:9 \| 4:3 \| 1:1 +2 `resolution`: 480p \| 720p \| 1080p `duration`: 2–30	All prices and parameters

What to check before integrating

Match price units: multiply a per-second rate by billable duration; for a generation tariff, inspect the exact duration tier. Reference-video inputs can have their own billing rules.
Check the allowed combination of duration, resolution, aspect ratio and audio. An enum lists individual options, not every valid combination.
Budget for several attempts per accepted shot. Test motion, text and identity continuity on your own material; there is no quality benchmark implied by this list.
Generation is asynchronous. Plan task polling or webhooks and download completed assets into your own storage. Validate input-media requirements before launching a batch.

Inspect a result before choosing

Veo 3.1 Quality: a close-up of melting icicles, with a slow zoom and visible water drops. This is an attributed vendor example, not an API Stock benchmark.

Source and license: Google AI for Developers, CC BY 4.0 · Format and dimensions adapted

Veo 3.1 Quality

One example shows a workflow, not a quality ranking. Compare your own brief across models before committing a production budget.

Prompt used for this example

{
  "prompt": "Close up shot (composition) of melting icicles (subject) on a frozen rock wall (context) with cool blue tones (ambiance), zoomed in (camera motion) maintaining close-up detail of water drips (action).",
  "aspectRatio": "16:9",
  "resolution": "720p"
}

Try this model in the playground

Compare model options

Guides

Questions before integrating

Which video generation API should I choose?

Choose the required input workflow first: text-only, an initial image or reference footage. Next check duration, resolution and audio. Compare candidate models on the same brief and settings; this category is a selection guide, not a universal quality ranking.

How much does AI video generation cost?

The table lists current starting prices and the unit each price buys. A per-second tariff needs the billable duration to calculate a clip price. Whole-generation tariffs can vary by duration, resolution and sound. Open the model’s full price table before estimating a batch.

Can I generate video from an image?

Use a model marked image-to-video. Check its image input fields and limits: a first frame, multiple reference images and a first/last-frame pair are different capabilities. The image-to-video guide explains how to prepare the source and describe motion.

Can I test models before integrating the API?

Open a model page and use its playground with your account balance. Review the estimated charge and input options before running it. The same model is available through the shared asynchronous generation API.