Pricing comparison

GPT-4.1 vs GPT-5

Per-token pricing, full-workload cost ladders, and monthly volume projections. Numbers sourced directly from each provider's rate card.

OpenAI

GPT-4.1

Input
$2.00 / 1M
Output
$8.00 / 1M
Cached input
$0.500 / 1M
Context
1.0M
Max output
33K

OpenAI

GPT-5

Input
$1.25 / 1M
Output
$10.00 / 1M
Cached input
$0.125 / 1M
Context
400K
Max output
128K

Cost per request

Four common workload shapes, input tokens and a 1:2 output ratio (a standard chat/completion pattern). Long-context surcharges apply automatically where the provider charges them.

ScenarioTokens (in / out)GPT-4.1GPT-5Winner
Short prompt100 / 200$0.0018$0.0021GPT-4.1
Typical request1,000 / 2,000$0.0180$0.0213GPT-4.1
Long document10,000 / 5,000$0.0600$0.0625GPT-4.1
Large prompt100,000 / 10,000$0.2800$0.2250GPT-5

Monthly bill at scale

Projected monthly cost at typical request volume, assuming the "typical request" shape above (1k in, 2k out).

TrafficReq / monthGPT-4.1GPT-5Delta
Small SaaS1,000$18.00$21.25GPT-4.1 -$3.25
Growing product10,000$180.00$212.50GPT-4.1 -$32.50
Heavy usage100,000$1,800$2,125GPT-4.1 -$325.00

Which should you use?

For the typical chat-shape request (~1k input, 2k output), GPT-4.1 comes out 18% cheaper. If you're picking one as the default, that's usually the right choice on cost alone.

Split decision: GPT-5 has the cheaper input rate, while GPT-4.1 has the cheaper output rate. RAG and long-context workloads favour the former; generation-heavy workloads (long responses, agentic loops) favour the latter.

Context window differs: GPT-4.1 holds 1.0M of input vs 400K on the other side. If you regularly push past the smaller ceiling, the comparison ends there.

Live cost calculator

Type in any token counts - both prices update instantly. Uses base input/output rates (no cache discount, no long-context tier).

GPT-4.1

$0.0060

per request

GPT-5

$0.0063

per request

GPT-4.1 is $0.0003 cheaper per request (4.0% less).

Try both in the estimator →

Drop your actual prompt in, tokens are counted with the provider's own tokenizer, and the dollar number matches what lands on your invoice.

Frequently asked

Which is cheaper, GPT-4.1 or GPT-5?
On a typical 1,000-input / 2,000-output request, GPT-4.1 costs ~$0.0180 vs ~$0.0213 on GPT-5. Input or output rates can flip the answer for very lopsided workloads - see the cost ladder above.
What's the difference in per-token pricing?
GPT-4.1 charges $2.00 per 1M input tokens and $8.00 per 1M output tokens. GPT-5 charges $1.25 / $10.00 per 1M.
Which has the bigger context window?
GPT-4.1 is larger (1.0M) vs 400K on the other.
Is there a cached-input discount on either?
GPT-4.1 caches at $0.500 per 1M (75% off). GPT-5 caches at $0.125 per 1M (90% off). Workloads with repeated static prefixes see the biggest savings.
How fresh is this comparison?
GPT-4.1 was re-verified on 2026-04-06 and GPT-5 on 2026-04-06 against each provider's published rate card. Calcis re-checks every row on a rolling schedule and re-deploys when a provider changes pricing.

GPT-4.1 verified 2026-04-06 · GPT-5 verified 2026-04-06. Rate cards at OpenAI and OpenAI.