Hacker News Reader

Comment by simonw | Hacker News Reader

I don't understand how the Claude functionality works.

As far as I know Anthropic haven't released the tokenizer for Claude - unlike OpenAI's tiktoken - but your tool lists the Claude 3 models as supported. How are you counting tokens for those?

View on HN

Anthropic actually has a Claude 3 tokenizer tucked away in one of their repos: https://github.com/anthropics/anthropic-tokenizer-typescript

At this moment, Tokencost uses the OpenAI tokenizer as a default tokenizer, but this would be a welcome PR!

"This package can be used to count tokens for Anthropic's older models. As of the Claude 3 models, this algorithm is no longer accurate [...]"

I've been bugging Anthropic about this for a while, they said that releasing a new tokenizer is not on their current roadmap.

Imagine a coffee shop refusing to have a price list until after the coffee's been made.

In many countries a taxi won't tell you how much the ride will cost. The first time I traveled to somewhere that negotiated the cost up front it blew my mind.

Frequently, contracts will have room for additional charges if circumstances change even a little, or products will have a market rate (fish, equity, etc.).

It might seem absurd but variable cost things are not uncommon.

In Oman, every tax fare was basically just of the bills. So 5 rials, 10 rials, or 20 rials. So many different ways people price things around the world.

In this case there's nothing that's variable, though, and the competition is able to pull it off precisely. Indeed, they themselves were able to do it before!

Perhaps they have a new tokenization method that's non-deterministic? If there are parallel lookaheads, not necessarily an rng, race conditions could make for variable cost. Or an expansion of certain terms into multiple token outputs, but the selection of which terms are expanded is based on a dynamic pool of Named Entities being recognized. Or maybe they just want to hide their process.. there is some secret sauce there even if it's deterministic, and so much depends on getting a good initial embedding, I've seen a tokenizer make or break an otherwise great model.

I am merely hypothesizing, it may not be nondeterministic but I'm not going to assume it's not.

> In many countries a taxi won't tell you how much the ride will cost.

I've only ever seen: fixed price based on destination (typically for fares originating from an airport), negotiated, or metered. A better analog analogy would be metered pricing, but where the cost per mile is a secret.

Where the cost per mile is published, but their mile ain’t yer mile.

These are called the variable variable costs now

This is what Washington DC did when I moved here. They theoretically had zones, but in reality it was arbitrary. Moving to meters was an amazing development.

Similarly, as LLMs become more and more commonplace, the pricing models will need to be more predictable. My LLM expenses are only around $100/month, but it's a bigger impediment to pushing projects to production when I can't tell the boss exactly how it'll be priced.

reminds me of the coffee shop incident in seattle last week with the hammer

I mean you already pay per output token and (sure, you can limit it), but it's unpredictable given the prompt?

It's open source so you can take a look (I'm not the author): https://github.com/AgentOps-AI/tokencost/blob/main/tokencost...

It looks like tiktoken is the default for most of the methods.

Disclaimer: I didn't fully trace which are being used in each case/model.

> # TODO: Add Claude support

There are no cases for Claude models yet.

I wonder if anyone has run a bunch of messages through Anthropic's API and used the returned token count to approximate the tokenizer?

Sorta: https://github.com/javirandor/anthropic-tokenizer

Yeah, I asked here because I dug around in the code and couldn't see how they were doing this, wanted to check I hadn't missed something.

Here you go https://github.com/javirandor/anthropic-tokenizer

Reply on news.ycombinator.com