1 million GPT-4.1 tokens cost $2.00 as input or $8.00 as output. Most workloads land in between — a 70/30 input/output split costs about $3.80. Verified Aug 16, 2026
Interactive calculator
1,000,000 in · 0 out
Input price
$2.00 / 1M tokens
Output price
$8.00 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 1 million tokens buys in practice
$3.20
80% input / 20% output — short replies over conversation history.
$2.60
90% input / 10% output — long retrieved context, grounded answers.
$2.30
95% input / 5% output — full documents in, structured extraction out.
Same 1 million tokens on other models
70/30 input/output split, uncached.
FAQ
1 million input tokens cost $2.00; 1 million output tokens cost $8.00. A typical 70/30 input/output mix costs about $3.80. Rates: $2.00/M input, $8.00/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 1 million tokens is roughly 208 requests. For a RAG workload with ~8,500 tokens per request, about 118 requests.
Yes — cached input costs $0.50/M instead of $2.00/M, a 75% discount on repeated context.