Pricing
Input 3 CNY / 1M tokens
Output 9 CNY / 1M tokens
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Capabilities
Input Types Text / Image
Output Types Text
Function Calling Supported
Session Cache Not supported
Fine-Tuning Supported
Prefix Cache Supported
Structured Output Supported
Image Understanding Supported
Text Generation Supported
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Open Source Status Closed source
Parameters
Last Updated 2026-07-11
Context Length 128K
Max Input Tokens 123K
Max Output Tokens 16K
Max Thought Tokens -
TPM -
RPM -
Parameter Count -
Modalities Vision and Text
Language Support English
Best For Vision understanding and document analysis
Resolution -
Video Duration -
Frame Rate -
Benchmarks
These benchmark scores summarize how the model performs across different tasks and evaluation sets.
HumanEval
92.1 Evaluates code generation correctness on programming tasks.