WAI pricing update #20118
WAI pricing update #20118
Conversation
github-actions
bot
added
the
product:workers-ai
|
Howdy and thanks for contributing to our repo. We review internal PRs with 1 week. If it's something urgent or has been sitting without a comment, start a thread in the Developer Docs space internally. |
| ## LLM model pricing | ||
| | Model | Price in Tokens | Price in Neurons | | ||
| | -------------------------------------------- | ---------------------------------------------------------- | ------------------------------------------------------------------------- | | ||
| | @cf/meta/llama-3.2-1b-instruct | $0.027 per M input tokens <br/> $0.201 per M output tokens | 2457 neurons per M input tokens <br/> 18252 neurons per M output tokens | |
There was a problem hiding this comment.
Would love to see this pull from the model info in the future. LGTM for clarity now!
There was a problem hiding this comment.
Yeah, agree that we'd want this pulled programmatically if possible.
The other bit here is -- if the data is pulled in programmatically -- we'd just want a pricing-specific section of the models pages (and likely not have direct pricing here). Dev lift for that is pretty minimal... dev lift for also showing those prices here is heavier.
rita3ko
requested review from
a team,
daisyfaithauma and
rita3ko
as code owners
| Workers AI has deprecated the usage of neurons in favor of unit-based pricing. The Cloudflare dashboards will be migrated this unit-based pricing soon so you can track your usage. Individual model pages will soon document the price for each model. We also made pricing cheaper! | ||
|
|
||
| We will begin billing for all models under this new pricing structure beginning November 1, 2024. | ||
| Workers AI has updated pricing to be more granular, with unit-based pricing presented to customers, but still billing in neurons in the back end. Blog post coming soon. |
There was a problem hiding this comment.
Ideally, docs shouldn't speak to points in time (has updated, coming soon), but might make sense in this case.
5 participants
Summary
Screenshots (optional)
Documentation checklist