Skip to content
AI Primer

BART

Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

A denoising sequence-to-sequence Transformer model family for natural-language generation, translation, and comprehension.

Pricing

Third-party research · Oct 21, 2026, 7:12 AM
Pricing notes were collected, but there are no normalized numeric fields to display yet.

Cloudflare listing: $0.00 per million input tokens for @cf/facebook/bart-large-cnn; output-token price is not stated. Listed as deprecated on 2026-05-30. No Meta first-party pricing found.

The Meta paper identifies BART as a text sequence-to-sequence model. Meta's source provides research/model information but no pricing. Cloudflare's provider documentation lists the hosted @cf/facebook/bart-large-cnn at $0.00 per million input tokens and says it was deprecated on 2026-05-30; it gives no output-token price. This is third-party hosting, not a Meta first-party price, and the incomplete token rates do not support a complete normalized token price finding.

View source

Model Intelligence

Benchmarkable
No
Model level
family

Recent stories

0 linked stories
No linked stories yet.
AI PrimerAI Primer

Your daily guide to AI tools, workflows, and creative inspiration.

© 2026 AI Primer. All rights reserved.