Hacker News Reader

Comment by TechDebtDevin | Hacker News Reader

Genuinely curious, What made you choose OpenAI as your preferred api provider? Its always been the least attractive to me.

View on HN

I have mainly been using Claude 3.5/3.6 Sonnet via API in the last several months (or since 3.5 Sonnet came out). However, I was using o1 for a challenging task at one point, but last I tested it had issues with some extra backslashes for that application.

I also have tested with DeepSeek R1 and will test some more with that although in a way Claude 3.6 with CoT is pretty good. Last time I tried to test R1 their API was out.

We extensively used the batch APIs to decrease cost and handle large amount of data. I also need JSON responses for a lot of things and OpenAI seem to have the best json schema output option out there.

I use it because my company bought the enterprise plan and trained a bunch of "specialist GPTs" that were fed internal documents, code bases, Slack threads etc. I am not aware of other good LLM companies providing the same level of integration.

Who else might be a good choice? Deepseek is down. Who has the cheapest gpt3.5 level or above api

Ive personaly been using Deepseek (which has been better than for 3.5 for a really long time), and Perplexity, which is nice for their built in search. Ive actually been using Deepseek since it was free. Its been generally good for me. Ive mostly chosen both because of pricing as I generally dont use APIs for extermely complex prompts.

Run it locally, the distilled smaller ones aren't bad at all.

Until recently they were the only game in town, so maybe they accrued significant spend back then?

Reply on news.ycombinator.com