Pricing comparison

GPT-4.1 mini vs DeepSeek V4 Pro

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

OpenAI

GPT-4.1 mini

Input
$0.40 / 1M
Output
$1.60 / 1M
Cached input
$0.100 / 1M
Context
1.0M
Max output
33K

DeepSeek

DeepSeek V4 Pro

Input
$1.74 / 1M
Output
$3.48 / 1M
Cached input
-
Context
1M
Max output
384K

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-4.1 miniDeepSeek V4 ProWinner
Short prompt100 / 200$0.0004$0.0009GPT-4.1 mini
Typical request1,000 / 2,000$0.0036$0.0087GPT-4.1 mini
Long document10,000 / 5,000$0.0120$0.0348GPT-4.1 mini
Large prompt100,000 / 10,000$0.0560$0.2088GPT-4.1 mini

Monthly bill at scale

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

TrafficReq / monthGPT-4.1 miniDeepSeek V4 ProDelta
Small SaaS1,000$3.60$8.70GPT-4.1 mini -$5.10
Growing product10,000$36.00$87.00GPT-4.1 mini -$51.00
Heavy usage100,000$360.00$870.00GPT-4.1 mini -$510.00

Which should you use?

For the typical chat-shape request (~1k input, 2k output), GPT-4.1 mini comes out 142% cheaper. If you're picking one as the default, that's usually the right choice on cost alone.

GPT-4.1 mini wins on both sides of the bill - cheaper input and cheaper output. If the quality gap is in your favour, there's no cost argument for the other side.

Context window differs: GPT-4.1 mini holds 1.0M of input vs 1M 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 mini

$0.0012

per request

DeepSeek V4 Pro

$0.0035

per request

GPT-4.1 mini is $0.0023 cheaper per request (65.5% 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 mini or DeepSeek V4 Pro?
On a typical 1,000-input / 2,000-output request, GPT-4.1 mini costs ~$0.0036 vs ~$0.0087 on DeepSeek V4 Pro. 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 mini charges $0.40 per 1M input tokens and $1.60 per 1M output tokens. DeepSeek V4 Pro charges $1.74 / $3.48 per 1M.
Which has the bigger context window?
GPT-4.1 mini is larger (1.0M) vs 1M on the other.
Is there a cached-input discount on either?
GPT-4.1 mini caches at $0.100 per 1M (75% off). DeepSeek V4 Pro does not publish a cached-input rate. Workloads with repeated static prefixes see the biggest savings.
How fresh is this comparison?
GPT-4.1 mini was re-verified on 2026-04-06 and DeepSeek V4 Pro on 2026-07-01 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 mini verified 2026-04-06 · DeepSeek V4 Pro verified 2026-07-01. Rate cards at OpenAI and DeepSeek.