GPT-4.1 in the API • Hacker News Board

Re: GPT-4.1 in the API

#51

Post by bobxmax » Mon, Apr 14, 2025, 5:23 PM UTC

codingwagie wrote: post #32

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.

Very easy with the naming system?

Really? Is o3-mini-high better than o1-pro?

Re: GPT-4.1 in the API

#52

Post by flakiness » Mon, Apr 14, 2025, 5:23 PM UTC

Big focus on coding. It feels like a defensive move against Claude (and more recently, Gemini Pro) which became very popular in that regime. I guess they recently figured out some ways to train the model for these "agentic" coding through RL or something - and the finding is too new to apply 4.5 on time.

Re: GPT-4.1 in the API

#53

Post by amarcheschi » Mon, Apr 14, 2025, 5:24 PM UTC

croes wrote: post #19

polytely wrote: post #18

It seems that OpenAI is really differentiating itself in the AI market by developing the most incomprehensible product names in the history of software.

They learned from the best: Microsoft

GpTeams Classic

Re: GPT-4.1 in the API

#54

Post by latexr » Mon, Apr 14, 2025, 5:25 PM UTC

codingwagie wrote: post #10

GPT-4.1 probably is a distilled version of GPT-4.5 I dont understand the constant complaining about naming conventions. The number system differentiates the models based on capability, any other method would not do that. After ten models with random names like "gemini", "nebula" you would have no idea which is which. Its a low IQ take. You dont name new versions of software as completely different software Also, Yest…

> You dont name new versions of software as completely different software

macOS releases would like a word with you.

https://en.wikipedia.org/wiki/MacOS#Timeline_of_releases

Technically they still have numbers, but Apple hides them in marketing copy.

https://www.apple.com/macos/

Though they still have “macOS” in the name. I’m being tongue-in-cheek.

Re: GPT-4.1 in the API

#55

Post by SubiculumCode » Mon, Apr 14, 2025, 5:27 PM UTC

codingwagie wrote: post #10

GPT-4.1 probably is a distilled version of GPT-4.5 I dont understand the constant complaining about naming conventions. The number system differentiates the models based on capability, any other method would not do that. After ten models with random names like "gemini", "nebula" you would have no idea which is which. Its a low IQ take. You dont name new versions of software as completely different software Also, Yest…

Feel free to lay the naming convention rules out for us man.

Re: GPT-4.1 in the API

#56

Post by exizt88 » Mon, Apr 14, 2025, 5:27 PM UTC

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…

> chatgpt-4o-latest, but it's bad because they continuously update it

Version explicitly marked as "latest" being continuously updated it? Crazy.

Re: GPT-4.1 in the API

#57

Post by minimaxir » Mon, Apr 14, 2025, 5:27 PM UTC

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…

OpenAI (and most LLM providers) allow model version pinning for exactly this reason, e.g. in the case of GPT-4o you can specify gpt-4o-2024-05-13, gpt-4o-2024-08-06, or gpt-4o-2024-11-20.

https://platform.openai.com/docs/models/gpt-4o

Re: GPT-4.1 in the API

#58

Post by granzymes » Mon, Apr 14, 2025, 5:28 PM UTC

croemer wrote: post #48

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…

So you're saying that "ChatGPT-4o-latest (2025-03-26)" in LMarena is 4.1?

No, that is saying that some of the improvements that went into 4.1 have also gone into ChatGPT, including chatgpt-4o-latest (2025-03-26).

Re: GPT-4.1 in the API

#59

Post by modeless » Mon, Apr 14, 2025, 5:28 PM UTC

Numbers for SWE-bench Verified, Aider Polyglot, cost per million output tokens, output tokens per second, and knowledge cutoff month/year:

             SWE  Aider Cost Fast Fresh
 Claude 3.7  70%  65%   $15  77   8/24
 Gemini 2.5  64%  69%   $10  200  1/25
 GPT-4.1     55%  53%   $8   169  6/24
 DeepSeek R1 49%  57%   $2.2 22   7/24
 Grok 3 Beta ?    53%   $15  ?    11/24

I'm not sure this is really an apples-to-apples comparison as it may involve different test scaffolding and levels of "thinking". Tokens per second numbers are from here: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25/pr... and I'm assuming 4.1 is the speed of 4o given the "latency" graph in the article putting them at the same latency.

Is it available in Cursor yet?

Re: GPT-4.1 in the API

#60

Post by msp26 » Mon, Apr 14, 2025, 5:28 PM UTC

I was hoping for native image gen in the API but better pricing is always appreciated.

Gemini was drastically cheaper for image/video analysis, I'll have to see how 4.1 mini and nano compare.