# Cherry 1.0 Pro

> Text- and image-to-video generation from 2 to 30 seconds at 1080p, 2K, or 4K with audio.

> Sakuranbo AI is in preview.

- Model ID: `sakuranbo/cherry-1.0-pro`
- Vendor: Sakuranbo AI
- Modality: Video
- Tasks: Text to video, Image to video, & Reference to video
- Upstream status: GA (upstream)
- Last updated: 2026-10-28
- HTML page: https://sakuranbo.ai/models/sakuranbo/cherry-1.0-pro/
- llms.txt: https://sakuranbo.ai/models/sakuranbo/cherry-1.0-pro/llms.txt

## Description

Cherry 1.0 Pro creates videos from a text prompt, from first and last keyframes, or from up to 10 reference images. Set the duration (2–30 s), resolution, and aspect ratio; audio is generated by default. Pricing is per second of output video by resolution.

## Capabilities

- Input: Text & Image
- Output: Video & Audio
- Resolutions: 1080p, 2k, 4k
- Aspect ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4
- Duration: 2 to 30 seconds
- Streaming: No
- Asynchronous job: Yes
- Audio output: Yes

## Parameters

| Name | Type | Required | Default | Constraints | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  | Up to 20,000 characters | Description of the scene, motion, and audio. |
| `first_frame` | url | No |  |  | Image to use as the first frame (image-to-video). |
| `last_frame` | url | No |  |  | Image to use as the last frame. Requires first_frame. |
| `reference_images` | url[] | No |  | Up to 10 items | Up to 10 reference images. Cannot be combined with keyframes. |
| `duration` | integer | No | `5` | 2 to 30 | Video length in seconds. Billed per second. |
| `resolution` | enum | No | `1080p` | One of: 1080p, 2k, 4k | Output resolution. Determines the per-second price. |
| `aspect_ratio` | enum | No | `adaptive` | One of: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4 | Aspect ratio of the output video. |
| `audio` | boolean | No | `true` |  | Generate an audio track. The price is the same with or without audio. |

## Pricing

Prices are in USD and include our margin. Failed, cancelled, expired, and policy-rejected runs are not billed. For chat, once the model has started generating output (including reasoning output), the output it generates is billed, even if the stream breaks or you close the connection.

| Dimension | Unit | Condition | Price |
| --- | --- | --- | --- |
| Output video | per second | resolution: 1080p | $0.225 |
| Output video | per second | resolution: 2k | $0.25 |
| Output video | per second | resolution: 4k | $0.2875 |

### Price examples

Examples use the listed prices. The server calculates the final charge from actual usage.

- Default run: $1.125 (5 s, 1080p)
- 5 s of video at 1080p: $1.125
- 5 s of video at 2K: $1.25
- 5 s of video at 4K: $1.4375
- 10 s of video at 1080p: $2.25
- 30 s of video at 1080p: $6.75

## API

### Estimate the price

POST /v1/estimate takes a JSON body ({ model, input }) and returns the price for that input before you run it. This endpoint does not need an API key.

```bash
curl -X POST "https://api.sakuranbo.ai/v1/estimate" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sakuranbo/cherry-1.0-pro",
  "input": {
    "prompt": "Aerial shot gliding over a misty mountain lake at sunrise, gentle wind and birdsong",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }
}'
```

### Generate

Send generation requests to /v1/videos. The request below uses an example input from the catalog for this model.

```bash
curl -X POST "https://api.sakuranbo.ai/v1/videos" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SAKURANBO_API_KEY" \
  -d '{
  "model": "sakuranbo/cherry-1.0-pro",
  "prompt": "Aerial shot gliding over a misty mountain lake at sunrise, gentle wind and birdsong",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "16:9"
}'
```

[Read the Videos guide](https://sakuranbo.ai/docs/videos/)

## Data policy

- Generated files are kept for 7 days and then deleted.
- Prompts are not stored. Only request metadata is kept.
- Your request is forwarded to an upstream provider that runs the model.

## Related models

- [CherryImage 1.0 Pro](https://sakuranbo.ai/models/sakuranbo/cherryimage-1.0-pro.md): High-fidelity text-to-image and reference-based image editing up to 2K resolution.
- [CherryText 1.0 Flash](https://sakuranbo.ai/models/sakuranbo/cherrytext-1.0-flash.md): Fast, low-cost language model with a 1M-token context window, tool calls, and reasoning.

Source: https://sakuranbo.ai/models/sakuranbo/cherry-1.0-pro/