Skip to content

GPT-4.1 mini API price, and what each result really costs

OpenAI, listed 14 Apr 2025. Price checked 12 Nov 2026; unchanged since we started tracking it. Source: OpenAI's pricing page. openai/gpt-4.1-mini

API shutdown on 2027-01-14. Suggested replacement: gpt-6-luna. What the switch to GPT-6 Luna costs

List price per million tokens

Input
$0.40
Cached input
$0.10
Output
$1.60
Context window
1.05M tokens

Note: API shutdown 2027-01-14; replacement gpt-6-luna.

What it costs per task, and per task that works

Six common task shapes with typical token counts. The real cost counts the tries that get redone; the rates are examples, not measurements.

TaskPer 1,000 triesPer 1,000 that work, 8 in 10Per 1,000 that work, 6 in 10Per 1,000 that work, 4 in 10
Support bot answer3,000 in / 300 out$1.68$2.10$2.80$4.20
Invoice field extraction2,500 in / 250 out$1.40$1.75$2.33$3.50
Lead scoring1,200 in / 100 out$0.64$0.80$1.07$1.60
Email reply draft1,500 in / 400 out$1.24$1.55$2.07$3.10
Translation900 in / 800 out$1.64$2.05$2.73$4.10
Search re-ranking4,000 in / 50 out$1.68$2.10$2.80$4.20

Work out your own real cost per resultTest GPT-4.1 mini on your own prompt

Compare GPT-4.1 mini with

Worked-through switches: GPT-4.1 mini → GPT-6 Luna: cost and quality on real tasks

Questions

How much does the GPT-4.1 mini API cost?

$0.40 per million input tokens and $1.60 per million output tokens, or $0.10 per million for cached input. Price checked 12 Nov 2026; unchanged since we started tracking it.

What does a result that works really cost with GPT-4.1 mini?

A support bot answer (about 3,000 tokens in, 300 out) costs $0.0017 per try. If 6 in 10 work first time, each answer that works really costs $0.0028, because the redone ones were paid for too.

Is GPT-4.1 mini being shut down?

OpenAI has announced the API shutdown of gpt-4.1-mini on 2027-01-14; the suggested replacement is gpt-6-luna. Source: https://developers.openai.com/api/docs/deprecations