GPT-4 Turbo vs o3-pro.
model vs model · prices as of
o3-pro takes 3 of 5 rounds against GPT-4 Turbo. GPT-4 Turbo counters on price: $54.55 per million tokens against $127.30, for 128k context instead of 200k.
OpenAIGPT-4 Turbo
$54.55/M tokens
cheapest we can explain, at Poe · $7.09 per 1,000 pages
128k context · tool calling · reads images
List price in (lower wins)
$30/M
$20/M
List price out (lower wins)
$60/M
$80/M
Cheapest we can explain (lower wins)
$54.55/M at Poe
$127.30/M at Poe
Standard price (lower wins)
$150/M
$140/M
Cost per 1,000 pages (lower wins)
$7.09
$15.27
Context
128k tokens
200k tokens
Open weights
no
no
Tool calling
yes
yes
Structured output
no
yes
Reads images
yes
yes
Reasoning
no
yes
Released
6 Nov 2023
10 Jun 2025
Providers selling it
18
12
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 7
Poe$54.55 / $127.30
Nous Portal$60 / $140- OpenAI$60 / $140
Eden AI$150 / $140
Kilo Gateway$150 / $140
OpenRouter$150 / $140
TrustedRouter$158.30 / $147.70
GPT-4 Turbo then o3-pro, 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
- GPT-4 TurboOpenAIOpenAI's list price, in and out per million tokens$10 / $30 $30 / $60150% dearer ·
- GPT-4 TurboNous Portal$24 / $48 $30 / $6025% dearer ·
- GPT-4 TurboNous Portal$8 / $24 $10 / $3025% dearer ·
- o3-proNous Portal$16 / $64 $20 / $8025% dearer ·
Frequently asked
- Which is cheaper, GPT-4 Turbo or o3-pro?
- GPT-4 Turbo, at $54.55 per million tokens against $127.30 for o3-pro, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- GPT-4 Turbo: $54.55 at Poe. o3-pro: $127.30 at Poe.
- Can I buy both from one provider?
- Yes. 7 providers sell both: Poe, Nous Portal, OpenAI, Eden AI, Kilo Gateway, OpenRouter, and more. The cheapest of them for the two together is Poe.
- Which holds more context?
- o3-pro, at 200k tokens against 128k.
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.