GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52

Simon Willison’s Weblog Subscribe Sponsored by: CodeRabbit — Planner helps 10x your coding agents while minimizing rework and AI slop. Try Now. GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52 OpenAI today: Introducing GPT‑5.4 mini and nano. These models join GPT-5.4 which was released two weeks ago. OpenAI’s self-reported benchmarks show the new 5.4-nano out-performing their previous GPT-5 mini model when run at maximum reasoning effort. The new mini is also 2x faster than the previous mini. Here’s how the pricing looks—gpt-5.4-nano is notably even cheaper than Google’s Gemini 3.1 Flash-Lite: Model Input Cached input Output gpt-5.4 $2.50 $0.25 $15.00 gpt-5.4-mini $0.75 $0.075 $4.50 gpt-5.4-nano $0.20 $0.02 $1.25 Other models for comparison Claude Opus 4.6 $5.00 - $25.00 Claude Sonnet 4.6 $3.00 - $15.00 Gemini 3.1 Pro $2.00 - $12.00 Claude Haiku 4.5 $1.00 - $5.00 Gemini 3.1 Flash-Lite $0.25 - $1.50 I used GPT-5.4 nano to generate a description of this photo I took at the John M. Mossman Lock Collection: llm -m gpt-5.4-nano -a IMG_2324.jpeg 'describe image' Here’s the output: The image shows the interior of a museum gallery with a long display wall. White-painted brick walls are covered with many framed portraits arranged in neat rows. Below the portraits, there are multiple glass display cases with dark wooden frames and glass tops/fronts, containing various old historical objects and equipment. The room has a polished wooden floor, hanging ceiling light fixtures/cords, and a few visible pipes near the top of the wall. In the foreground, glass cases run along the length of the room, reflecting items from other sections of the gallery. That took 2,751 input tokens and 112 output tokens, at a cost of 0.069 cents (less than a tenth of a cent). That means describing every single photo in my 76,000 photo collection would cost around $52.44. I released llm 0.29 with support for the new models. Then I had OpenAI Codex loop through all five reasoning effort levels and all three models and produce this combined SVG grid of pelicans riding bicycles (generation transcripts here). I do like the gpt-5.4 xhigh one the best, it has a good bicycle (with nice spokes) and the pelican has a fish in its beak! Posted 17th March 2026 at 7:39 pm · Follow me on Mastodon, Bluesky, Twitter or subscribe to my newsletter More recent articles My fireside chat about agentic engineering at the Pragmatic Summit - 14th March 2026 Perhaps not Boring Technology after all - 9th March 2026 This is GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52 by Simon Willison, posted on 17th March 2026. ai 1916 openai 402 generative-ai 1699 llms 1665 llm 565 vision-llms 84 llm-pricing 67 pelican-riding-a-bicycle 101 llm-release 185 Previous: My fireside chat about agentic engineering at the Pragmatic Summit Monthly briefing Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments. Pay me to send you less! Sponsor & subscribe Disclosures Colophon © 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026