Video Generationtextimagevideoaudio

Berry 1.0

CarrotHub Berry 1.0 全能视频生成模型，基于 Wan 3.0 Standard。

输入

生成方式

仅使用文本描述生成视频，无需上传图片。

提示词

参考图（可选）

支持 PNG、JPG、WebP · 可将文件拖到此区域

Duration

230

Resolution

Aspect ratio

Prompt extend

Generate audio

准备开始生成

API 参考

POSThttps://api.token360.ai/v1/videos

# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "berry-1.0",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "adaptive",
  "prompt_extend": true,
  "generate_audio": true
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"

API 文档

Overview#

CarrotHub Berry 1.0 all-in-one video generation, based on Wan 3.0 Standard. The model supports text-to-video, first/last-frame image-to-video, and multimodal reference-to-video through POST /v1/videos.

Output controls#

Duration is 2-30 seconds or -1 for smart duration. Supported resolutions: 480p, 720p, 1080p. Aspect ratios: adaptive, 16:9, 4:3, 1:1, 3:4, and 9:16. Audio and prompt extension default to enabled.

Pricing#

480p: $0.050/second
720p: $0.100/second
1080p: $0.200/second

Upstream reference#

https://www.mulerouter.ai/docs/api-reference/endpoint/carrothub/berry-1.0/generation