Pricing
Input 0.49 CNY / 1M tokens
Output 2.1 CNY / 1M tokens
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Capabilities
Input Types Video / Image / Audio / Text
Output Types Text
Function Calling -
Session Cache -
Fine-Tuning -
Prefix Cache -
Structured Output -
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 2026-06-23
Context Length 1048K
Max Input Tokens 1000K
Max Output Tokens 65K
Max Thought Tokens -
TPM 4000K
RPM 4K
Parameter Count 8B params
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.
GPQA
38.4 Evaluates graduate-level science knowledge and reasoning ability.
MMLU Pro
58.7 Tests multidisciplinary knowledge, comprehension, and reasoning.