logoalt Hacker News

holistio • today at 4:14 AM • 10 replies • view on HN

You pay $200/month to Anthropic, $200/month to OpenAI, $200/month to Cursor, $200/month to $200/month to Google, and seeing that it didn't come to a nice round $1024/month, you pay $200/month to Sakana to coordinate it all, because why not.

While you're at it, feel free to send me $200 as well, I'll generate a crypto address ending with "AI".

Replies

ricardobeat • today at 2:16 PM

My current setup:

    $20/month: Claude Code
    $10/month: Minimax
    $16/month: Xiaomi Mimo
    $10/month: Opencode Go
Opus at low/medium effort generates plans. Then several coordinator/worker pairs are possible: DeepSeek v4 Pro + Minimax M3, Mimo v2.5 Pro + Mimo v2.5, Mimo + Minimax, Sonnet 4.6 + Haiku. I've been running hundreds of long multi-agent sessions, topped up extra credits here and theere, but haven't reached $200/month spend yet. Relying entirely on Claude/Codex feels like a waste of cash now.
holistio • today at 4:17 AM

TIL: I just found out that base58 disallows I (capital i), l (lowercase L), O (capital o) and 0 (zero), so I could only generate GrxoJt4eNXE2QaQ55iPSa7hhiYdzCo8ZeAuokmh2Cai.

(don't send anything, sharing only because of the base58 fun fact I didn't know)

robertwt7 • today at 5:36 AM

at this point I might just try Neuralwatt and see how much request I can get with GLM5.2. I've read a lot of reviews that its very cheap to run using Neuralwatt cloud

bicx • today at 2:06 PM

I wish I only paid $200/mo for Anthropic! Multiply that by 20x.

➕ show 1 reply
JumpCrisscross • today at 8:36 AM

Does it work? I’m less interested in economics than fit with an MVP.

➕ show 1 reply
someone_1234 • today at 5:10 AM

Or use openrouter and switch to model you want to use..(i think so)

➕ show 1 reply
rvz • today at 4:28 AM

Pay $0 to run a local model or even a cheap DeepSeek V4 model via their API which is close to free per million tokens.

These prices are just going to get raced to $0.

➕ show 2 replies
da_grift_shift • today at 9:36 AM

Yo dawg, I heard you like agents, so we put agents in yo agents so you can burn tokens while you burn tokens.

emodendroket • today at 3:19 PM

[dead]

audreyt • today at 4:56 AM

Happy user here, pairing it with Composer 2.5, with Fugu Ultra as advisor and Fugur as planner. For scope/architecture it’s on par with useful Fable-style orchestration than one chat thread.

I've been shipping production on archive.tw with Fugu Ultra in /advisor on oh-my-pi.

Advisor doesn’t slow the loop if the driver stays fast. Worth it if your harness can split advisor from worker.