About
A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an...
Related Models
Pricing
Input
$0.07
per 1M tokens
Output
$0.28
per 1M tokens
Blended
$0.12
per 1M tokens
Cheaper than 81% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.12
Monthly
$3.68
vs. Similar Models
Baidu: ERNIE 4.5 21B A3B Thinking
$0.120%
Meta: Llama 3.2 3B Instruct
$0.12-0%
Reka Flash 3
$0.13+2%
Olmo 3 7B Instruct
$0.13+2%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
8K
tokens
6% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame