o3-mini vs o4 Mini High.
model vs model · prices as of
o3-mini takes 1 of 5 rounds against o4 Mini High. It is also the cheaper of the two to run, at $7 per million tokens against $7.70.
OpenAIwins 1 roundso3-mini
$7/M tokens
cheapest we can explain, at Poe · $0.84 per 1,000 pages
200k context · tool calling
OpenAIo4 Mini High
$7.70/M tokens
OpenAI list price, nothing below it is accounted for · $0.924 per 1,000 pages
200k context · tool calling · reads images
List price in (lower wins)
$1.10/M
$1.10/M
List price out (lower wins)
$4.40/M
$4.40/M
Cheapest we can explain (lower wins)
$7/M at Poe
none below list
Standard price (lower wins)
$7.70/M
$7.70/M
Cost per 1,000 pages (lower wins)
$0.84
$0.924
Context
200k tokens
200k tokens
Open weights
no
not stated
Tool calling
yes
yes
Structured output
yes
yes
Reads images
no
yes
Reasoning
yes
yes
Released
20 Dec 2024
16 Apr 2025
Providers selling it
22
6
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not stated
no provider to check
Providers selling both · 6
FastRouter$7.70 / $7.70
Kilo Gateway$7.70 / $7.70
NanoGPT$7.70 / $7.70
Nous Portal$7.70 / $7.70- OpenAI$7.70 / $7.70
OpenRouter$7.70 / $7.70
o3-mini then o4 Mini High, per million tokens
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- o3-miniNous Portal$0.88 / $3.52 $1.10 / $4.4025% dearer ·
- o4 Mini HighNous Portal$0.88 / $3.52 $1.10 / $4.4025% dearer ·
Frequently asked
- Which is cheaper, o3-mini or o4 Mini High?
- o3-mini, at $7 per million tokens against $7.70 for o4 Mini High, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- o3-mini: $7 at Poe. o4 Mini High: nobody goes below the maker's own price with a reason we can point at, so $7.70 is the number to beat.
- Can I buy both from one provider?
- Yes. 6 providers sell both: FastRouter, Kilo Gateway, NanoGPT, Nous Portal, OpenAI, OpenRouter. The cheapest of them for the two together is FastRouter.
- Which holds more context?
- Both hold 200k tokens in one call.
Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.