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
Output Types Text
Function Calling Supported
Session Cache Not supported
Fine-Tuning Supported
Prefix Cache Not supported
Structured Output Not supported
Image Understanding Supported
Text Generation -
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Open Source Status -
Parameters
Last Updated 2026-07-23
Context Length 32K
Max Input Tokens 32K
Max Output Tokens 12K
Max Thought Tokens -
TPM 5000K
RPM 30K
Parameter Count -
Modalities Text and Image
Language Support English
Best For Intent recognition
Resolution -
Video Duration -
Frame Rate -
Benchmarks
These benchmark scores summarize how the model performs across different tasks and evaluation sets.
AIME
86.7 Measures performance on difficult competition-level mathematics problems.
GPQA
77.3 Evaluates graduate-level science knowledge and reasoning ability.