Pricing
Input 0.75 CNY / 1M tokens
Output -
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Capabilities
Input Types -
Output Types -
Function Calling -
Session Cache -
Fine-Tuning -
Prefix Cache -
Structured Output -
Image Understanding -
Text Generation Supported
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Open Source Status -
Parameters
Last Updated 2026-07-25
Context Length -
Max Input Tokens -
Max Output Tokens -
Max Thought Tokens -
TPM -
RPM -
Parameter Count 30.5B params
Modalities Text
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
85 Measures performance on difficult competition-level mathematics problems.
GPQA
73.4 Evaluates graduate-level science knowledge and reasoning ability.
LiveCodeBench
66 Benchmarks code understanding and real-world coding task performance.
HumanEval
60 Evaluates code generation correctness on programming tasks.
MMLU Pro
80.9 Tests multidisciplinary knowledge, comprehension, and reasoning.