Pricing
Input 1 CNY / 1M tokens
Output -
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 Not supported
Prefix Cache 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 2026-07-17
Context Length 8K
Max Input Tokens 32K
Max Output Tokens 8K
Max Thought Tokens -
TPM -
RPM -
Parameter Count 8B 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
50.4 Measures performance on difficult competition-level mathematics problems.
GPQA
49 Evaluates graduate-level science knowledge and reasoning ability.
LiveCodeBench
39.6 Benchmarks code understanding and real-world coding task performance.
Math500
89.1 Measures accuracy on a focused set of mathematics benchmark questions.