Process massive datasets with rerank-qa-mistral-4b, featuring an expansive 128K context window for long-document analysis. This model delivers available completely free of charge, open weights architecture. Access rerank-qa-mistral-4b via the Nvidia API with up to 4K output tokens.
Tokens
Tokens
Tokens
rerank-qa-mistral-4b by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.