Pricing
Input 2 CNY / 1M tokens
Output 8 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 Supported
Image Understanding Not supported
Text Generation Supported
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Open Source Status Open source
Parameters
Last Updated 2026-09-01
Context Length 128K
Max Input Tokens 128K
Max Output Tokens 32K
Max Thought Tokens -
TPM -
RPM -
Parameter Count 355B params
Modalities Text
Language Support English
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
91 Measures performance on difficult competition-level mathematics problems.
GPQA
79.1 Evaluates graduate-level science knowledge and reasoning ability.
LiveCodeBench
72.9 Benchmarks code understanding and real-world coding task performance.
HLE
14.4 Reports the model's overall aggregate benchmark score.
Math500
98.2 Measures accuracy on a focused set of mathematics benchmark questions.
MMLU Pro
84.6 Tests multidisciplinary knowledge, comprehension, and reasoning.
SciCode
41.7 Measures performance in scientific coding and technical workflows.