Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-4.1 in the API

openai.com

Post reply on HN
Print view View original

61–70 of 513 posts

Re: GPT-4.1 in the API

#61

Post by henlobenlo »

School-Cotton wrote: post #45
Philpax wrote: post #29

Earlier quoted context omitted.

> The number system differentiates the models based on capability, any other method would not do that. Please rank GPT-4, GPT-4 Turbo, GPT-4o, GPT-4.1-nano, GPT-4.1-mini, GPT-4.1, GPT-4.5, o1-mini, o1, o1 pro, o3-mini, o3-mini-high, o3, and o4-mini in terms of capability without consulting any documentation.

Btw, as someone who agrees with your point, what’s the actual answer to this?

Whats the problem, for the layman it doesnt actually matter, and for the experts, its usually very obvious which model to use.

Re: GPT-4.1 in the API

#62

Post by florakel »

themanmaran wrote: post #44
yberreby wrote: post #20

> Note that GPT‑4.1 will only be available via the API. In ChatGPT, many of the improvements in instruction following, coding, and intelligence have been gradually incorporated into the latest version (opens in a new window) of GPT‑4o, and we will continue to incorporate more with future releases. The lack of availability in ChatGPT is disappointing, and they're playing on ambiguity here. They are framing this as if…

I disagree. From the average user perspective, it's quite confusing to see half a dozen models to choose from in the UI. In an ideal world, ChatGPT would just abstract away the decision. So I don't need to be an expert in the relatively minor differences between each model to have a good experience. Vs in the API, I want to have very strict versioning of the models I'm using. And so letting me run by own evals and pi…

> it's quite confusing to see half a dozen models to choose from in the UI. In an ideal world, ChatGPT would just abstract away the decision

Supposedly that’s coming with GPT 5.

Re: GPT-4.1 in the API

#63

Post by yberreby »

themanmaran wrote: post #44
yberreby wrote: post #20

> Note that GPT‑4.1 will only be available via the API. In ChatGPT, many of the improvements in instruction following, coding, and intelligence have been gradually incorporated into the latest version (opens in a new window) of GPT‑4o, and we will continue to incorporate more with future releases. The lack of availability in ChatGPT is disappointing, and they're playing on ambiguity here. They are framing this as if…

I disagree. From the average user perspective, it's quite confusing to see half a dozen models to choose from in the UI. In an ideal world, ChatGPT would just abstract away the decision. So I don't need to be an expert in the relatively minor differences between each model to have a good experience. Vs in the API, I want to have very strict versioning of the models I'm using. And so letting me run by own evals and pi…

I agree on both naming on stability. However, this wasn't my point.

They still have a mess of models in ChatGPT for now, and it doesn't look like this is going to get better immediately (even though for GPT-5, they ostensibly want to unify them). You have to choose among all of them anyway.

I'd like to be able to choose 4.1.

Re: GPT-4.1 in the API

#64

Post by minimaxir »

School-Cotton wrote: post #45
Philpax wrote: post #29

Earlier quoted context omitted.

> The number system differentiates the models based on capability, any other method would not do that. Please rank GPT-4, GPT-4 Turbo, GPT-4o, GPT-4.1-nano, GPT-4.1-mini, GPT-4.1, GPT-4.5, o1-mini, o1, o1 pro, o3-mini, o3-mini-high, o3, and o4-mini in terms of capability without consulting any documentation.

Btw, as someone who agrees with your point, what’s the actual answer to this?

It depends on how you define "capability" since that's different for reasoning and nonreasoning models.

Re: GPT-4.1 in the API

#65

Post by oofbaroomf »

I'm not really bullish on OpenAI. Why would they only compare with their own models? The only explanation could be that they aren't as competitive with other labs as they were before.

Re: GPT-4.1 in the API

#66

Post by ilaksh »

Tiberium wrote: post #42

Very important note: >Note that GPT‑4.1 will only be available via the API. In ChatGPT, many of the improvements in instruction following, coding, and intelligence have been gradually incorporated into the latest version If anyone here doesn't know, OpenAI does offer the ChatGPT model version in the API as chatgpt-4o-latest, but it's bad because they continuously update it so businesses can't reliably rely on it bein…

Yeah, in the last week, I had seen a strong benchmark for chatgpt-4o-latest and tried it for a client's use case. I ended up wasting like 4 days, because after my initial strong test results, in the following days, it gave results that were inconsistent and poor, and sometimes just outputting spaces.

Re: GPT-4.1 in the API

#68

Post by yberreby »

Tiberium wrote: post #49
yberreby wrote: post #20

> Note that GPT‑4.1 will only be available via the API. In ChatGPT, many of the improvements in instruction following, coding, and intelligence have been gradually incorporated into the latest version (opens in a new window) of GPT‑4o, and we will continue to incorporate more with future releases. The lack of availability in ChatGPT is disappointing, and they're playing on ambiguity here. They are framing this as if…

There's a HUGE difference that you are not mentioning: there are "gpt-4o" and "chatgpt-4o-latest" on the API. The former is the stable version (there are a few snapshot but the newest snapshot has been there for a while), and the latter is the fine-tuned version that they often update on ChatGPT. All those benchmarks were done for the API stable version of GPT-4o, since that's what businesses rely on, not on "chatgpt…

Good point, but how does that relate to, or explain, the decision not to release 4.1 in ChatGPT? If they have a nice post-training pipeline to make 4o "nicer" to talk to, why not use it to fine-tune the base 4.1 into e.g. chatgpt-4.1-latest?

Re: GPT-4.1 in the API

#69

Post by glenstein »

meetpateltech wrote: post #23

GPT-4.1 Pricing (per 1M tokens): gpt-4.1 - Input: $2.00 - Cached Input: $0.50 - Output: $8.00 gpt-4.1-mini - Input: $0.40 - Cached Input: $0.10 - Output: $1.60 gpt-4.1-nano - Input: $0.10 - Cached Input: $0.025 - Output: $0.40

Awesome, thank you for posting. As someone who regularly uses 4o mini from the API, any guesses or intuitions about the performance of Nano?

I'm not as concerned about nomenclature as other people, which I think is too often reacting to a headline as opposed to the article. But in this case, I'm not sure if I'm supposed to understand nano as categorically different than many in terms of what it means as a variation from a core model.

Re: GPT-4.1 in the API

#70

Post by poormathskills »

ZeroCool2u wrote: post #8

No benchmark comparisons to other models, especially Gemini 2.5 Pro, is telling.

Go look at their past blog posts. OpenAI only ever benchmarks against their own models.

This is pretty common across industries. The leader doesn’t compare themselves to the competition.

Post reply on HN