GPT-4.1 vs GPT-5 mini

GPT-5 mini is cheaper for every workload modelled here.

List prices checked

Specifications and rates

PropertyGPT-4.1GPT-5 mini
Input per 1M$2.00$0.250
Output per 1M$8.00$2.00
Cached input per 1M$0.500$0.025
Blended (3:1)$3.50$0.688
Context window1M400K
Max output33K128K
Inputs acceptedtext, imagetext, image

Source: OpenAI pricing (May 2026) · OpenAI pricing (May 2026). Published list prices only — committed-use discounts, regional variation, and per-request charges are not included. Not yet independently re-checked against the vendor’s page.

Monthly cost by workload

Identical token volumes through both rate cards. Output-heavy profiles are where the ranking flips.

WorkloadGPT-4.1GPT-5 miniCheaper
In-app chat assistantA support or help assistant handling a few thousand conversations a month, with short prompts and short answers.$80$15GPT-5 minisaves $65/mo (81%)
RAG over documentsRetrieval-augmented answering where each request stuffs several retrieved passages into the prompt, so input dominates.$720$105GPT-5 minisaves $615/mo (85%)
Coding agentAn agentic loop that reads files and writes patches, generating heavy output and re-sending large context on every turn.$1,600$300GPT-5 minisaves $1,300/mo (81%)

What each one is for

GPT-4.1

by OpenAI

A million-token context window at a mid-tier price, which remains the reason to reach for it over newer models when the whole codebase has to fit in one request.

GPT-5 mini

by OpenAI

A fifth of GPT-5's price with the same 400k context window, which makes it the cheapest way to process very long documents without dropping to a small model.

Common questions

Is GPT-4.1 or GPT-5 mini cheaper in 2026?
GPT-5 mini, for every workload modelled here. On a blended 3:1 basis it costs $0.688 per million tokens against GPT-4.1's $3.50.
Which has the larger context window?
GPT-4.1, at 1M tokens against 400K. A larger window only helps if you can afford to fill it — the cost of one full-context request is in the table above.
Which is cheaper for output-heavy work like agents?
GPT-5 mini, at $2.00 per million output tokens against $8.00. Reasoning tokens bill as output, so for agentic loops this axis usually decides the invoice regardless of what the input rates look like.
What is not included in these figures?
Batch-processing discounts, fine-tuning, long-context surcharges above a provider's standard tier, and any enterprise agreement. These are published pay-as-you-go list prices, checked against each provider's own pricing page on the date shown.

Other model comparisons