GPT-4 Turbo vs GPT-5 Pro
Prices checked
GPT-4 Turbo takes 3 of 5 rounds against GPT-5 Pro. It is also the cheaper of the two to run, at $13.50 per million tokens against $37.50.
OpenAIWins 3 roundsGPT-4 Turbo
128k context · tool calling · reads images
$13.50/M tokensCheapest price, at Poe · $7.02 per 1,000 pages
OpenAIGPT-5 Pro
400k context · tool calling · reads images
$37.50/M tokensCheapest price, at Poe · $14.73 per 1,000 pages
Maker's price in (lower wins)
$30/M
$15/M
Maker's price out (lower wins)
$60/M
$120/M
Cheapest price (lower wins)
$13.50/M at Poe
$37.50/M at Poe
Maker's price, blended (lower wins)
$37.50/M
$41.25/M
Cost per 1,000 pages (lower wins)
$7.02
$14.73
Context
128k tokens
400k tokens
Open weights
no
no
Tool calling
yes
yes
Structured output
no
yes
Reads images
yes
yes
Reasoning
no
yes
Released
6 Nov 2023
6 Oct 2025
Providers selling it
13
19
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not published
not published
Providers selling both · 8
Poe$13.50 / $37.50- OpenAI$15 / $41.25
Azure AI Foundry$37.50 / $41.25
Eden AI$37.50 / $41.25
Kilo Gateway$37.50 / $41.25
Nous Portal$37.50 / $41.25
OpenRouter$37.50 / $41.25
OrcaRouter$37.50 / $41.25
GPT-4 Turbo, then GPT-5 Pro, per million tokens.
Go further
Add a third or fourth model, or change the weighting, in the tool.
Frequently asked
- Which is cheaper, GPT-4 Turbo or GPT-5 Pro?
- GPT-4 Turbo, at $13.50 per million tokens against $37.50 for GPT-5 Pro, blended 3 in : 1 out, read on 31 Oct 2026.
- Where is each one cheapest?
- GPT-4 Turbo: $13.50 at Poe. GPT-5 Pro: $37.50 at Poe.
- Can I buy both from one provider?
- Yes. 8 providers sell both: Poe, OpenAI, Azure AI Foundry, Eden AI, Kilo Gateway, Nous Portal, and more. The cheapest of them for the two together is Poe.
- Which holds more context?
- GPT-5 Pro, at 400k tokens against 128k.
Prices exclude tax, read 31 Oct 2026 from each provider's own catalog. They are per M tokens, blended 3 in : 1 out, and a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.
Related comparisons