Compare Models

Run side-by-side checks for pricing, context window, and latency.

bart-large-cnn

facebook

BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.

Context window: — tokens
Input cost: $0.00 / 1M
Output cost: $0.00 / 1M
Latency (p50): —

View full profile →