Hacker News Reader

HNHacker News

Top New Best Ask Show Jobs

Comment by londons_explore | Hacker News Reader

Full thread

londons_explore·

You can still run the original gpt-4-0314 model (March 14th) on the API playground:

https://platform.openai.com/playground?mode=chat&model=gpt-4...

Costs $0.12 per thousand tokens (~words), and I find even fairly heavy use rarely exceeds a dollar a day.

View on HN

How hard is it to get GPT-4 API access?

I get "The model: `gpt-4-0314` does not exist".

You probably don't have access. I'm not sure what the exact access requirements are - I think you either have to be a GPT Plus subscriber, have contributed code to an OpenAI repo on github, or be on one of their lists of researchers.

Try gpt-3.5-turbo-0301 - I think everyone has access to that.

FWIW, I'm a GPT Plus subscriber and haven't been given API access to GPT-4 despite being on the waiting list for as long as it's been up. I'm told that submitting evaluations can move you up in the queue, but I haven't tried that.

https://openai.com/waitlist/gpt-4-api

"During the gradual rollout of GPT-4, we’re prioritizing API access to developers that contribute exceptional model evaluations to OpenAI Evals to learn how we can improve the model for everyone."

So are you sure that isn't also nerfed?

It hasn't been changed since March 14th... So it's equally nerfed as it was then...

Also, the playground lets you set the 'system message', which you can use to tell it to answer questions even if the results may be dangerous/rude/inappropriate.

I have been using the API. There are conflicting reports in this thread that seems to indicate it may also be affected. I am not sure.

Did you set the model code to gpt-4-0314?

I did, and I still get the original speed (produces tokens at about the speed you would read aloud), and I haven't seen quality change.

Reply on news.ycombinator.com