Tell HN: Anthropic's Fable model is too expensive

OpenCode has a generous $10 plan for open weight models, I'm quite happy with it

https://opencode.ai/docs/go/

Fireworks.ai has a $50 plan in early access

https://docs.fireworks.ai/firepass

I'm shopping around for more good deals like this, I'm long on open weights and sour on Big Ai

Too expensive, yet probably still too cheap to make up for their cost of developing and running it. Don’t expect prices to go down. Or if they superficially go down, the models just consume more tokens per task so your bill still increases in the end.

Guys, are we poor? I just ran out after a 20 minute refactoring exercise for the next 4.5 hours lol.

Suggestion: run this command:

  uvx agentsview usage daily

That should tell me the token total and dollar cost across all of your local coding agents.

If it doesn't seem to know how much Fable costs you can follow these instructions to teach it the Fable pricing scheme, then run the command a second time to see the results: https://til.simonwillison.net/llms/agentsview-custom-model-p...

I've not run into the same Fable quota problems that others have reported myself yet. I wonder if people are running prompts that are somehow spinning up a ton of subagents?

built this to stop fable blowing up my usage limit https://github.com/teamchong/pxpipe

Currently Fable is available through Chinese resellers at around ~$17.50/1M tokens, or about a 65% discount vs API prices. Still expensive compared to Opus.

Sometimes I think about how much power I'm using with 10 Fable agents running in parallel for 10 minutes each. It's gotta be a lot. Compared to my PC which with a great GPU can run a crap agent that takes way too long and does a terrible job at everything.

Anyways, I don't get it, do you wish they never released Fable? I can't believe they're making any money on it. I'd bet they said we're gonna burn 100 million dollars on 12 days of unlimited access just to at least give people a taste and maybe recoup our losses if people actually pay for it later.

Currently running an experiment where I'm using Fable as a planner/orchestrator/verifier and using Mimo 2.5 as subagents/builders. Seems to be doing well with my old specs.

Fable so far has only been incrementally better than Opus 4.8 in my testing. The testing so far has been coding on a large monolith. In general Claude is starting to feel like it's optimize for greenfield vibe-coding projects. I vastly prefer Codex for coding on large, established codebases.

Well, as predicted I see many here complaining about how expensive Fable is. [0]

It is not just companies that know it is economically expensive, but it is also expensive to companies who have zero-data retention policies and they cannot offer AI features that use this model.

Anthropic doesn't care and won't talk to you unless you're paying them hundreds of millions. There are now local models which are great alternatives which have no quotas and can work with companies that have zero data retention policies.

[0] https://news.ycombinator.com/item?id=48467112

Wait till June 22nd! That'll be like $5000/week usage. This may be the cheapest Fable-class or better Anthropic model you ever see in your lifetime.

(Anthropic has said they want to get Fable back on to subscription plans at some point.)

Doesn't even seem that great, to me. Granted it was one day of work where i didn't use it particularly heavily. But i tried to lean into the "use a background agent for everything" thing but i didn't get a ton done past what i had to do by hand (manually deploying changes, testing them, moving on: we're switching hosting providers, gotta make sure updates keep rolling, no way for Claude to do it outside handing over the prod S3 keys which, not even Fable lol)

Can anyone account for the wild inconsistency between people's reports of session usage? I would hear stories of people saying they burned their weekly quota in 30 minutes, and then there's this post. Yet I used Fable exclusively today across multiple work projects fairly extensively and haven't cracked 20%.