GPT-4o is $2.50 per million input tokens and $10 per million output tokens. GPT-4o mini is $0.15 and $0.60. The mini cache read is $0.075, against $1.25 for GPT-4o. Both list a 128,000 token context window. Mini is the much smaller bill. It is a different model, so a cheaper total does not mean the same reply. Both are older models that OpenAI still lists with a price.
For 1,000 input tokens, 400 output tokens, and 50 requests a day, in US dollars: GPT-4o mini is the cheapest of these, at $0.59 a month.
$0.0004 for one request, and $0.02 a day at 50 requests a day.
Show the maths
New input: 1,000 tokens × $0.15 per million = $0.0002
Output: 400 tokens × $0.60 per million = $0.0002
1,500 requests a month × $0.0004 = $0.59
Caching half the input would save about $0.06 a month
That uses the published cache-read price of $0.08 per million tokens. It assumes half of these input tokens are already in a cache. Writing the cache can cost extra, and that write price is not included.
Batch processing would save about $0.29 a month
OpenAI's batch table lists half the standard input and output price for this model. Batch jobs are slower, and they suit work that can wait.
GPT-4.1 nano would cost about $0.19 less a month
It is a cheaper model in the same broad class on this price list. It is still a different model, and the replies will not match.
A reply half as long would save about $0.18 a month
Output tokens are often the expensive part. Asking for a shorter answer cuts that cost directly.
$0.0065 for one request, and $0.33 a day at 50 requests a day.
Show the maths
New input: 1,000 tokens × $2.50 per million = $0.0025
Output: 400 tokens × $10.00 per million = $0.004
1,500 requests a month × $0.0065 = $9.75
Caching half the input would save about $0.94 a month
That uses the published cache-read price of $1.25 per million tokens. It assumes half of these input tokens are already in a cache. Writing the cache can cost extra, and that write price is not included.
Batch processing would save about $4.88 a month
OpenAI's batch table lists half the standard input and output price for this model. Batch jobs are slower, and they suit work that can wait.
GPT-4.1 would cost about $1.95 less a month
It is a cheaper model in the same broad class on this price list. It is still a different model, and the replies will not match.
A reply half as long would save about $3.00 a month
Output tokens are often the expensive part. Asking for a shorter answer cuts that cost directly.
Cached prices here are read prices. Writing a cache can cost extra, and that write price is on the provider’s page, not in this total. A US-only endpoint is 1.1× at some providers and is not included. Fast modes are not included.