Post

New release of my llm-openai plugin supporting today's three new GPT-4.1 models from OpenAI: llm install -U llm-openai-plugin llm -m openai/gpt-4.1 "Generate an SVG of a pelican riding a bicycle" github.com/simonw/llm-o...

Simon Willison

@simonwillison.net

14 Apr 2025

My notes on the GPT-4.1 series so far - 1m tokens (across all three models) and GPT-4.1-nano being their cheapest model yet are particularly notable simonwillison.net/2025/Apr/14/...

simonwillison.netGPT-4.1: Three new million token input models from OpenAI, including their cheapest model yetOpenAI introduced three new models this morning: GPT-4.1, GPT-4.1 mini and GPT-4.1 nano. These are API-only models right now, not available through the ChatGPT interface (though you can try them …

Simon Willison

@simonwillison.net

Added this note to my post to help illustrate how absurdly inexpensive these models have got now. I can use GPT-4.1 nano to generate descriptions of 4,000 images for less than a dollar!

14/4/25, 7:54 pm2 reposts31 likes

Bornach

@bornach.bsky.social

14 Apr 2025

Could it be a loss leader? We're all gonna end up paying the full cost of it later.

Simon Willison

@simonwillison.net

14 Apr 2025

My hunch is that this is their workhorse model that they're hoping people will fire trillions of tokens through, and as such they're not running it at a loss

Martín Gaitán

@tinnqn.bsky.social

15 Apr 2025

wouldn't be nice to integrate the calculator in the log --usage output? or maybe like --usage --estimate-cost ?

Simon Willison

@simonwillison.net

15 Apr 2025

I've been nervous about doing that because I don't want to provide incorrect estimates if the model prices change, but maybe I'm overthinking it

Martín Gaitán

@tinnqn.bsky.social

15 Apr 2025

As on the web, a note saying "[*] prices may have changed" seems fair enough. In fact, it could fetch the price list dynamically from the web, so you could update it independently of LLM itself.