2026-04-25 13:29:37
Big sigh a relief from Spurs fans tonight. Whew. This team is well coached. Love seeing Dylan Harper show up just when he’s needed. Steph Castle great too. 🏀
2026-04-25 12:45:45
If the announcers say that Wemby is out one more time I’m going to lose my mind. Yes, we know! 🏀
2026-04-25 10:49:55
Tonight UT is remembering staff and faculty who have passed away by darkening the tower except for two rings of lights near the top. We sat for a while and listened to the bells.
2026-04-25 04:42:17
I’ve been trying to find the right balance of AI models to use in Micro.blog. Currently we use a few different flavors of GPT, including OpenAI’s cheaper “flex” version when speed doesn’t matter much, such as in the background work that powers Inkwell’s Reading Recap feature.
API pricing is a little all over the map, so I thought I’d capture some of the recent prices here, for OpenAI and Anthropic. I’m including a couple older models too, like the retired GPT-4.5. This is per million tokens, input / output.
GPT-5.5: $5.00 / $30
GPT-5.4: $2.50 / $15
GPT-5.4 Mini: $0.75 / $4.50
GPT-5.4 Nano: $0.20 / $1.25
GPT-5: $1.25 / $10
GPT-4.5: $75.00 / $150
Opus 4.7: $5.00 / $25
Opus 4.6: $5.00 / $25
Opus 4: $15.00 / $75
Sonnet 4.6: $3.00 / $15
Haiku 4.5: $1.00 / $5
What can we learn from this? I have no idea. Clearly GPT-4.5 was a gigantic model, and so OpenAI changed course into more efficient models. Opus has generally been more expensive, but now is comparable to GPT-5.5.
2026-04-25 03:32:04
Marked-up Mac minis on Ebay, going for almost $1k… Nutty. Better to just get a MacBook Neo.