Pricing
Input 0.7 CNY / 1M tokens
Output 2.8 CNY / 1M tokens
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Capabilities
Input Types Text / Image / Audio / Video
Output Types Text
Function Calling Supported
Session Cache -
Fine-Tuning -
Prefix Cache -
Structured Output Supported
Image Understanding Supported
Text Generation Supported
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Open Source Status Open source
Parameters
Last Updated 2026-09-11
Context Length 1048K
Max Input Tokens 1024K
Max Output Tokens 64K
Max Thought Tokens -
TPM -
RPM -
Parameter Count -
Modalities Multimodal
Language Support Multilingual
Best For General AI application workflows
Resolution -
Video Duration -
Frame Rate -
Benchmarks
These benchmark scores summarize how the model performs across different tasks and evaluation sets.
AIME
49.8 Measures performance on difficult competition-level mathematics problems.
GPQA
64.6 Evaluates graduate-level science knowledge and reasoning ability.
LiveCodeBench
33.7 Benchmarks code understanding and real-world coding task performance.