Ask HN: What are some economical ways to access LLMs?

[yangikan]

Want to hear about your experiences in terms of cost from various providers of LLM APIs. For example, for my usecase, I don't need to have a real time response. Are there any services that exploit spot instances and such, where I can submit a set of queries and get responses after a few hours, but costs much less?

[dartos]

The secret sauce is using a big LLM to generate many “responses” for some given intents, then use phi or something cheap to do intent detection and pick one of the pre made responses.

You can generate 100s of responses per intent, so the user may not ever get the same response twice.

Ofc it depends on your use case, but smoke and mirrors are your friend.

[yangikan]

Please post articles comparing the pricing of API providers. I have heard nice things about together.ai