2h ago

@nrehiew_ says Opus 4.7 and GPT 5.5 effective costs converge because developers reject more GPT 5.5 code

Mean agent request costs vary 9x across evaluated model families.

——0——
Original post
OPeric zakariasson#1965eric zakariasson@ERICZAKARIASSON

the economics of intelligence > Cost per agent request varies by nearly 9x across model families, showing that the same workflow can have very different cost profiles depending on the model behind it. some higher cost models are cheaper in the long run due to increased intelligence, but for p50 requests a model like composer 2.5 will do the job both faster and cheaper a lot of interesting data in this report, recommend a read

9:01 AM · May 28, 2026 View on X
QUOTE POSTwh#1430wh@NREHIEW_

Despite GPT 5.5 having a higher output price than Opus 4.7, Cursor found that Opus4.7 Agent requests are almost double the cost of GPT 5.5's.

But, normalized for % of lines accepted, both models end up in similar cost territory, which indicates more lines from 5.5 are rejected

4:46 PM · May 28, 2026 · 1.7K Views
@nrehiew_ says Opus 4.7 and GPT 5.5 effective costs converge because developers reject more GPT 5.5 code · Digg