Image to Video API
UnificAlly serves 42 image to video models from Kling, MiniMax, ByteDance, Alibaba, Google, xAI and Vidu through one REST API and one API key. Rates start at $0.007/sec (SeeDance 1.5 Pro) or $0.075 per video (Veo 3.1), depending on how each model bills, and you pay per generation from a prepaid balance with no subscription. Every model below uses the same two calls: POST /v1/tasks to start a job and GET /v1/tasks/{task_id} to fetch the result.
To animate a start frame and pin the frames in between, the Kling 4.0 API takes up to 10 keyframes; the Grok Imagine API page has the speed-optimized route from a single image.
All 42 image to video models on UnificAlly
| Model | Provider | Starting rate |
|---|---|---|
| Gemini Omni Flash 1.2 API Any length from 3 to 15s, character references with voice presets, and video editing up to 15s. | from $0.0213/sec | |
| MiniMax H3 Highspeed API MiniMax The faster H3: 768p, 4-15s, start/end frames, up to 9 reference images and 3 reference videos, native audio. | MiniMax | $0.054/sec |
| MiniMax H3 Fast API MiniMax About 30 s a job: 480p or 768p, 4-15s, start/end frames, up to 9 reference images with no per-image charge, 3 reference videos and 3 audio clips. | MiniMax | from $0.0414/sec |
| MiniMax H3 Lite API MiniMax H3 inputs at about half the price: 480p or 768p, 4-15s, start/end frames, up to 9 reference images and 3 reference videos. | MiniMax | from $0.0225/sec |
| MiniMax H3 Max API MiniMax 480p or 768p, 5-15s, start/end frames, up to 9 reference images, 3 reference videos and 3 audio clips, seed and prompt expansion. | MiniMax | from $0.045/sec |
| MiniMax H3 Max Turbo API MiniMax Distilled H3 Max: text or start/end frames only, 480p or 768p, 5-15s, six aspect ratios, seed and prompt expansion. | MiniMax | from $0.0225/sec |
| Grok Imagine 1.5 Lite Video API xAI Cheapest Grok video: T2V or I2V, 1–15s, 480p to 1080p, with sound. | xAI | from $0.01/sec |
| Kling 4.0 API Kling 3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. | Kling | from $0.126/sec |
| Vidu Q4 API Vidu Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio. | Vidu | from $0.036/sec |
| Kling 4.0 Flash API Kling The fast Kling 4.0 model. 3-20s at 720p with stereo audio, from text, a start frame, or up to 10 reference images. | Kling | from $0.0756/sec |
| Gemini Omni Flash 1.1 API Text, image, and character references with voice presets; 4-10s videos plus conversational editing. | from $0.11 per video | |
| Wan 3.0 Prime API Alibaba Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times. | Alibaba | from $0.0612/sec |
| Wan 3.0 API Alibaba 2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P. | Alibaba | from $0.0425/sec |
| SeeDance 2.5 API ByteDance 4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references. | ByteDance | from $0.114/sec |
| MiniMax Hailuo H3 API MiniMax 2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, up to 9 reference images and 3 reference videos. | MiniMax | from $0.072/sec |
| HappyHorse 1.1 API Alibaba Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass. | Alibaba | from $0.112/sec |
| Kling 3.0 Turbo API Kling T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio. | Kling | from $0.1008/sec |
| Veo 3.1 API 4 model variants, 720p–4K, lip-synced dialogue and SFX in one call. | from $0.075 per video | |
| SeeDance 2.0 API ByteDance Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro. | ByteDance | from $0.022/sec |
| SeeDance 2.0 Fast API ByteDance Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround. | ByteDance | from $0.0372/sec |
| SeeDance 2.0 Mini API ByteDance Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized. | ByteDance | from $0.022/sec |
| Kling 3.0 API Kling Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync. | Kling | from $0.0756/sec |
| Grok Imagine 1.5 Fast Video API xAI T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p. | xAI | from $0.04/sec |
| Grok Imagine 1.5 Video API xAI T2V, I2V or 14 references, end frame, voices, 1–15s at native 1080p. | xAI | from $0.04/sec |
| Kling O1 API Kling Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p. | Kling | from $0.0756/sec |
| MiniMax Hailuo 2.0 API MiniMax Prompt alone, a start frame, or start and end frames, 768p or 1080p, 6 or 10 seconds. | MiniMax | from $0.0504/sec |
| MiniMax Hailuo 2.3 API MiniMax Prompt alone or with a start frame, 768p or 1080p, 6 or 10 seconds. | MiniMax | from $0.042/sec |
| MiniMax Hailuo 2.3 Fast API MiniMax Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds. | MiniMax | from $0.0285/sec |
| Kling 2.1 API Kling I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects. | Kling | from $0.0504/sec |
| Kling 2.1 Master API Kling T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music. | Kling | $0.252/sec |
| Kling 2.5 Turbo API Kling T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro. | Kling | from $0.0378/sec |
| Kling 2.6 Motion Control API Kling Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro. | Kling | from $0.063/sec |
| Kling 3.0 Motion Control API Kling Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro. | Kling | from $0.1134/sec |
| Kling 2.6 API Kling T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio. | Kling | from $0.0378/sec |
| SeeDance 1.5 Pro API ByteDance T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos. | ByteDance | from $0.007/sec |
| Wan 2.6 API Alibaba T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot. | Alibaba | from $0.09/sec |
| SeeDance 1.0 API ByteDance T2V or I2V at 480p/720p, 5 or 10 second clips. | ByteDance | from $0.015/sec |
| SeeDance 1.0 Pro API ByteDance First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds. | ByteDance | from $0.022/sec |
| SeeDance 1.0 Pro Fast API ByteDance Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds. | ByteDance | from $0.007/sec |
| Kling 3.0 Omni API Kling Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode. | Kling | from $0.0756/sec |
| Wan 2.7 API Alibaba T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P. | Alibaba | from $0.09/sec |
| HappyHorse 1.0 API Alibaba T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video. | Alibaba | from $0.119/sec |
How to call the Image to Video API
Every model takes the same request: a model ID and an input object. This example uses google/veo-3.1-fast; swap in any model ID from the table and the input fields from its model page.
# 1. Start a task
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "google/veo-3.1-fast",
"input": {
"prompt": "Camera slowly zooms in",
"start_image_url": "https://example.com/start.jpg",
"aspect_ratio": "16:9",
"duration": 6
}
}'
# 2. Read the result with the task_id from step 1
curl https://api.unifically.com/v1/tasks/TASK_ID \
-H "Authorization: Bearer YOUR_API_KEY"Image to Video API FAQ
- How much does the Image to Video API cost?
- Each model has its own rate, shown in the table above and on the pricing page. The lowest listed rates right now are $0.007/sec (SeeDance 1.5 Pro) and $0.075 per video (Veo 3.1). You pay per generation from a prepaid balance: no subscription, no monthly minimum, and the balance does not expire. Failed generations are not charged, and a request with dry_run set to true returns the exact price without running the job.
- How do I call these image to video models from code?
- Send POST https://api.unifically.com/v1/tasks with your API key, a model ID (for example google/veo-3.1-fast) and an input object. The response holds a task_id: poll GET /v1/tasks/{task_id} until the status is completed, or pass a callback_url to receive the result by webhook. The request shape is the same for every model; only the model ID and the input fields change.
- How do I send the source image?
- Pass a public image URL in the model's input. The field name depends on the model (Veo 3.1 uses start_image_url, with an optional end_image_url for the last frame) and each model page lists its parameters. If the image is not hosted anywhere yet, upload it to UnificAlly file storage first and use the URL it returns.
- Can I try the image to video models before topping up?
- Yes. A new UnificAlly account starts with a $0.50 signup balance, and every model page has a browser playground that runs on it, so you can compare outputs before writing any code. Your first top-up of $25 or more adds a $5 bonus.