Loading...
Loading...
A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing. Built with scaling-efficient infrastructure for high-throughput training and inference, the model leverages advanced post-training techniques including SFT, DPO, and UPO for optimized performance, while supporting an impressive 131K context length and RLVR alignment for superior cross-modal reasoning and generation capabilities.
Price/1M
$0.25
305th cheapest
21% below median
Top 45%
Context Window
30K
323rd largest
Top 92%
Input
$0.14
per 1M tokens
Output
$0.56
per 1M tokens
Blended
$0.25
per 1M tokens
Cheaper than 55% of models. Median price is $0.31/1M tokens.
Daily
$0.25
Monthly
$7.35
Context Window
30K
tokens
Larger than 8% of models
Max Output
8K
tokens
27% of context
Context Window Comparison