Pricing
Input -
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 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 2026-06-28
Context Length -
Max Input Tokens -
Max Output Tokens -
Max Thought Tokens -
TPM -
RPM -
Parameter Count 21B params
Modalities Text
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.
Math Index
78.4 Captures broad mathematical problem-solving and reasoning performance.
HumanEval
62.3 Evaluates code generation correctness on programming tasks.