Flash — fastest and cheapest, lighter reasoningCommercial API

GPT-4.1 Mini (batch) Pricing

OpenAI · openai-gpt-4-1-mini-batch

ShareX Facebook LinkedIn

Input / 1M tokens

$0.200

Output / 1M tokens

$0.800

Context window

1,047,576 tokens

≈ 1,397 pages of text

Max output

32,768 tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0006

1,000 requests / month$0.56/mo 10,000 requests / month$5.60/mo 100,000 requests / month$56.00/mo

Estimate your own workloadOpens the calculator with GPT-4.1 Mini (batch) preloaded — adjust volume and token counts there.

Price history

Only one price point recorded so far.

The staircase chart appears once a price change is detected.

What it excels at

Efficient for high-volume batch text and vision tasks with 1M context; low per-token cost supports large-scale classification and extraction workloads.

The business tradeoff

Reasoning depth is lower than flagship GPT models; performance on complex multi-step or nuanced tasks can be inconsistent.

Cheaper from OpenAI

GPT-5.4 Nano (batch)OpenAI$0.0004/ typical request gpt-oss-120bOpenAI$0.0001/ typical request

Same tier from other providers

Claude Haiku 4.5Anthropic$0.0032/ typical request Gemini 3.5 FlashGoogle$0.0054/ typical request Llama 3.3 70BMeta$0.0003/ typical request

Head-to-head

GPT-4.1 Mini (batch) vs Claude Haiku 4.5 →GPT-4.1 Mini (batch) vs Gemini 3.5 Flash →GPT-4.1 Mini (batch) vs Llama 3.3 70B →

Vendor list rates, as of Jul 22, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.