Thanks, that did work! https://
gist.github.com/simonw/0f1a370
92fd0814bae75050eced48889#raw-json-response
… – the thing that confused me most is that it doesn't report "reasoning" tokens as a separate line item any more, see comment at the bottom of my Gist
@simonw
-
Reasoning Tokens Not Reported Separately in API Response
By
–
-
Claude Code vs OpenAI Codex: Competitive Race Heats Up
By
–
My hunch for now is that this was an ill-considered test which they didn't anticipate would be instantly spotted and cause (justified) uproar – here's hoping they decide that the "test" isn't a good idea! If they do go ahead I expect OpenAI Codex to catch Claude Code very fast
-
Anthropic Drops Claude Code From $20 Monthly Plan
By
–
This is so confusing. Did Anthropic really just drop Claude Code from their $20/month plan? Why would they do that through a pricing page update without making a proper announcement? Plus, $20/month still gets you Cowork, which is just Claude Code wearing a non-threatening hat!
-
OpenAI Uses Multiple Names for New Image Generation Model
By
–
True to form, I've already seen OpenAI themselves refer to the new image model as "ChatGPT Images 2.0", "Image gen 2" and "gpt-image-2"
-
Testing ChatGPT Images With a Creative Where’s Waldo Benchmark
By
–
I came up with a somewhat foolish new benchmark for testing image generation models, to exercise the new ChatGPT Images 2.0: "Do a where's Waldo style image but it's where is the raccoon holding a ham radio"
-
Forcing Extended Thinking in Claude Opus 4.7 Image Generation
By
–
This piece thinks that the reason I got a crap pelican riding a bicycle from Opus 4.7 is that it didn't think about it first, I'm trying to figure out if there's a way to force it to think that I've missed
-
Claude Opus 4.7 Extended Thinking API Budget Tokens Availability
By
–
Claude Opus 4.7 with adaptive thinking via the API… am I missing something or is it not possible any more to force it to think? (Prompt hacks like "think step by step" don't count here, I mean the equivalent of budget_tokens or effort: high in previous Claude models)
-
OpenAI Euphony Tool Mirrors Codex Transcript Viewer Design
By
–
OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://t.co/lUQQds4Nvj https://t.co/lI8h72reKy
— Simon Willison (@simonw) 21 avril 2026OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://
tools.simonwillison.net/codex-timeline
?url=httpsgist.githubusercontent.comsimonwa9eb5993a2853ec840d26c0e56bde362rawb8c5febdf60d878da84e27c07efdaed159abde4alogs.jsonl#tz=local&q=&type=all&payload=all&role=all&hide=1&truncate=1
… -
Session Export Format Remains Challenging for Users
By
–
Still too hard to export a session in a format I can publish and share with other people
-
Qwen reasoning traces praised for poetic quality
By
–
I always enjoy the Qwen reasoning traces but this one was particularly poetic