Skip to content
OpenRouter

BART Large CNN (Summary)

flagship
Meta · released 2019-10-01 · text
currently routing · 4.2k rpm
1.0M tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
open
License
/ ABOUT

BART Large CNN is a sequence-to-sequence model from Meta, specifically fine-tuned for text summarization on the CNN/DailyMail dataset. Built on the BART (Bidirectional and Auto-Regressive Transformers) architecture, it generates concise, fluent summaries of news articles and other long-form text.

The model uses a denoising autoencoder pretraining approach, learning to reconstruct corrupted text, which gives it strong abstractive summarization capabilities. It produces summaries that capture key information while maintaining readability and factual accuracy.

BART Large CNN remains one of the most popular open summarization models, widely used in news aggregation, document summarization, and content condensation applications.

Providers for BART Large CNN (Summary)

1 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
bf16
0.00%