GPT-4.1 vs o3.
model vs model · prices as of
GPT-4.1 takes 1 of 5 rounds against o3. Both cost $12.73 per million tokens to run.
OpenAIwins 1 roundsGPT-4.1
$12.73/M tokens
cheapest we can explain, at Poe · $1.53 per 1,000 pages
1M context · tool calling · reads images
List price in (lower wins)
$2/M
$2/M
List price out (lower wins)
$8/M
$8/M
Cheapest we can explain (lower wins)
$12.73/M at Poe
$12.73/M at Poe
Standard price (lower wins)
$14/M
$14/M
Cost per 1,000 pages (lower wins)
$1.53
$1.53
Context
1M tokens
200k tokens
Open weights
no
no
Tool calling
yes
yes
Structured output
yes
yes
Reads images
yes
yes
Reasoning
no
yes
Released
14 Apr 2025
16 Apr 2025
Providers selling it
30
24
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 · 24
Poe$12.73 / $12.73
302.AI$14 / $14
Abacus$14 / $14
Azure AI Foundry$14 / $14
Azure Cognitive Services$14 / $14
Cloudflare AI Gateway$14 / $14
FastRouter$14 / $14
Helicone$14 / $14
GPT-4.1 then o3, per million tokens · showing the 8 cheapest of 24
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
Frequently asked
- Which is cheaper, GPT-4.1 or o3?
- Neither: both run at $12.73 per million tokens, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- GPT-4.1: $12.73 at Poe. o3: $12.73 at Poe.
- Can I buy both from one provider?
- Yes. 24 providers sell both: Poe, 302.AI, Abacus, Azure AI Foundry, Azure Cognitive Services, Cloudflare AI Gateway, and more. The cheapest of them for the two together is Poe.
- Which holds more context?
- GPT-4.1, at 1M tokens against 200k.
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.