Pricing
Input 0 CNY / 1M tokens
Output 0 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 2026-05-09
Context Length 200K
Max Input Tokens 200K
Max Output Tokens 16K
Max Thought Tokens -
TPM -
RPM -
Parameter Count 9B 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.
Math Index
72.5 Captures broad mathematical problem-solving and reasoning performance.
Math500
89.3 Measures accuracy on a focused set of mathematics benchmark questions.
HumanEval
28.7 Evaluates code generation correctness on programming tasks.
Coding Index
28.7 Summarizes overall coding capability across supported tasks.