OpenAI

GPT-4.1 mini pricing

Previous-generation mini at 1M context. 5x cheaper than full 4.1 for compatible workloads.

Input

$0.40/ 1M tok

Output

$1.60/ 1M tok

Context window
1.0M
Max output
33K
Cached input
$0.100 / 1M
Verified
2026-04-06

GPT-4.1 mini carries the 1M context window of the full GPT-4.1 at a fraction of the price: $0.40 per 1M input and $1.60 per 1M output. For document-heavy workloads that need the full million tokens of context but don't need the flagship's capability, this is often the right landing spot.

A 10K-token prompt with a 2K-token reply costs about $0.0072 on 4.1 mini - versus $0.028 on full 4.1 for the same shape. Cached input at $0.10 per 1M (a 75% discount) is less aggressive than the 90% on GPT-5-era models, but still substantial for repeated-prefix document workflows.

Calcis counts GPT-4.1 mini input tokens with o200k_base (tiktoken), the same tokenizer OpenAI uses for billing - so the token count you see before you send matches the one that lands on your invoice.

Estimate your cost on GPT-4.1 mini

Paste your prompt into the estimator, pick GPT-4.1 mini, and see the exact dollar cost - input tokens counted with the provider's own tokenizer, output tokens predicted by our regression model.

Open cost calculator →

Frequently asked

When should I pick GPT-4.1 mini over GPT-5 mini?
Pick 4.1 mini when you need a 1M context window (GPT-5 mini tops out at 400K). On pure price, GPT-5 mini is cheaper at $0.25/$2 per 1M vs 4.1 mini's $0.40/$1.60 - but context size flips the decision for long-document work.
How much does GPT-4.1 mini cost per request?
A 1,000-token prompt with a 500-token reply costs about $0.0012 ($0.0004 input + $0.0008 output). At 1 million requests a month, that's around $1,200.
Does GPT-4.1 mini support the full 1M context?
Yes - 1,047,576-token context window, same as full GPT-4.1. Max output is 32,768 tokens.
What's the cached input discount on GPT-4.1 mini?
$0.10 per 1M cached tokens - a 75% discount on the standard $0.40 input rate. Automatic when prompt prefixes repeat within 5 minutes.

Pricing verified 2026-04-06 from the provider's rate card.