Pricing
Input -
Output -
Text to Image -
Image to Image -
Text to Video -
Image to Video -1 CNY / 1M tokens
Capabilities
Input Types Image
Output Types Audio
Function Calling -
Session Cache -
Fine-Tuning -
Prefix Cache -
Structured Output -
Image Understanding -
Text Generation -
Text to Image -
Image to Image -
Text to Video Not supported
Image to Video Supported
Open Source Status Closed source
Parameters
Last Updated 2026-07-21
Context Length -
Max Input Tokens -
Max Output Tokens -
Max Thought Tokens -
TPM -
RPM 0K
Parameter Count -
Modalities Text and Video
Language Support English
Best For Video generation and motion content production
Resolution 16:9 / 9:16 / 1:1 / 4:3 / 3:4 / Original
Video Duration 5 s
Frame Rate 24 FPS