Amazon
Amazon: Nova Pro 1.0
amazon/nova-pro-v1
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX). Amazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents. **NOTE**: Video input is not supported at this time.
/ 1M tokens
/ 1M tokens
tokens
Limits
Context
300,000
tokens
Max output
5,120
1.7% of the context window
Model facts
Author
Amazon
Tokenizer
Nova
Modality
Text + Image -> Text
Knowledge cutoff
2024-10-31
Created
Dec 5, 2024
Publication status
Modalities
Generation controls
Capability scores
Better than 10% of models compared
Creative tasks
Category performance
798 Elo
21.4% win