Pricing
Input 4 CNY / 1M tokens
Output 12 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 Not 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 -
Parameters
Last Updated 2026-08-27
Context Length 128K
Max Input Tokens 96K
Max Output Tokens 32K
Max Thought Tokens 32K
TPM 5000K
RPM 30K
Parameter Count 671B params
Modalities Multimodal
Language Support English
Best For Reasoning, planning, and complex problem solving
Resolution -
Video Duration -
Frame Rate -
Benchmarks
These benchmark scores summarize how the model performs across different tasks and evaluation sets.
AIME
88.4 Measures performance on difficult competition-level mathematics problems.
GPQA
59 Evaluates graduate-level science knowledge and reasoning ability.
LiveCodeBench
74.8 Benchmarks code understanding and real-world coding task performance.
MMLU Pro
75.9 Tests multidisciplinary knowledge, comprehension, and reasoning.
Coding Index
71.6 Summarizes overall coding capability across supported tasks.