←back to thread

514 points mfiguiere | 8 comments | | HN request time: 0s | source | bottom
Show context
cglong ◴[] No.43709527[source]
There's a lot of tools now with a similar feature set. IMO, the main value prop an official OpenAI client could provide would be to share ChatGPT's free tier vs. requiring an API key. They probably couldn't open-source it then, but it'd still be more valuable to me than the alternatives.
replies(2): >>43709642 #>>43709643 #
cube2222 ◴[] No.43709643[source]
Coding agents use extreme numbers of tokens, you’d be getting rate limited effectively immediately.

A typical small-medium PR with Claude Code for me is ~$10-15 of API credits.

replies(5): >>43709683 #>>43709757 #>>43709762 #>>43710075 #>>43710866 #
1. ai-christianson ◴[] No.43709762[source]
I've ended up with $5K+ in a month using sonnet 3.7, had to dial it back.

I'm much happier with gemini 2.5 pro right now for high performance at a much more reasonable cost (primarily using with RA.Aid, but I've tried it with Windsurf, cline, and roo.)

replies(3): >>43709859 #>>43709893 #>>43710779 #
2. triyambakam ◴[] No.43709859[source]
That's the largest I've heard of. Can you share more detail about what you're working on that consumes so many tokens?
replies(1): >>43715845 #
3. skeptrune ◴[] No.43709893[source]
Hoooly hell. I swear the AI coding products are basically slot machines.
replies(1): >>43712590 #
4. ilrwbwrkhv ◴[] No.43710779[source]
Just try the most superior model deep-seek
5. Implicated ◴[] No.43712590[source]
Or the people using them are literally clueless.
6. ai-christianson ◴[] No.43715845[source]
It's really easy to get to $100 in a day using sonnet 3.7 or o3 in a coding agent.

Do that every day for a month and you're already at $3k/month.

It's not hard to get to $5k from there.

replies(1): >>43726006 #
7. triyambakam ◴[] No.43726006{3}[source]
Sure but how? Still wondering more specifically what you're doing. And 3-5k is unfortunately my entire month's salary
replies(1): >>43727813 #
8. ai-christianson ◴[] No.43727813{4}[source]
I'm developing an open source coding agent (RA.Aid).

I'm using RA.Aid to develop itself (dogfooding,) so I'm constantly running the coding agent.

That cost is my peak cost, not average.

It's easy to scale back costs to 1/10 the cost and still get 90% of the quality. Basically that means using models like gemini 2.5 pro or Deepseek v3 (even cheaper) rather than expensive models like sonnet 3.7 and o3.