GPT-5.2 vs GPT-5.1: cost compared

Last verified

GPT-5.1 is 29% cheaper on input and 29% cheaper on output than GPT-5.2. Whether that makes it the right choice depends entirely on whether it does your task well enough — this page gives you the cost side of that trade, precisely.

Rates side by side

$ per million tokensGPT-5.2GPT-5.1
Input$1.75$1.25
Output$14.00$10.00
Cached input$0.17$0.13
Output : input ratio8.0×8.0×

What the difference is worth

Monthly cost for the same workload on each, without caching:

WorkloadGPT-5.2GPT-5.1Difference
Support chatbot
1,000 conversations/month · 2,000 in + 500 out each
$10.50$7.50$3.00 saved
RAG search
10,000 queries/month · 8,000 in + 400 out each
$196$140$56.00 saved
Bulk extraction
10,000 documents · 3,000 in + 300 out each
$94.50$67.50$27.00 saved
Coding agent
100 runs/month · 400,000 in + 20,000 out each
$98.00$70.00$28.00 saved

Which to use

GPT-5.1 if the task is well-specified and mechanical — extraction, classification, formatting, routine transformation. The saving is real and compounds with volume.

GPT-5.2 if the task involves genuine reasoning, long-horizon planning, or work where a wrong answer is expensive to catch. Paying 1.4× more on input is trivial compared to the cost of shipping a bad result.

Both are OpenAI models, so switching is usually a one-line change and the tokenizer is the same — which makes this a genuinely easy experiment to run. Test on your own workload before deciding.

Don't skip caching

Cached input costs $0.17 on GPT-5.2 and $0.13 on GPT-5.1. If your prompts share a stable prefix, caching on the more expensive model can beat switching to the cheaper one outright — worth checking before you migrate anything.

Sources

OpenAI rates verified 2026-08-05 (source). OpenAI rates verified 2026-08-05 (source).