GPT-4o mini API Cost Calculator

OpenAI's GPT-4o mini: $0.15/M input · $0.6/M output · $0.075/M cached input. Price your own workload below.

Presets:

What GPT-4o mini costs in practice

WorkloadInputOutputCost
Short chat message500250$0.0002
10-page document + summary7,000500$0.0014
Agent / coding session50,00010,000$0.013
1M tokens in + 1M out1,000,0001,000,000$0.750

GPT-4o mini vs nearest rivals

Closest-priced alternatives on a mixed 10K-input / 2K-output request:

ModelInput $/MTokOutput $/MTokMixed request
GPT-4o mini$0.15$0.6$0.0027
Gemini 2.5 Flash-Lite$0.1$0.4$0.0018
DeepSeek V4 Flash$0.14$0.28$0.0020
Mistral Small 4$0.15$0.6$0.0027

Frequently asked questions

How much does the GPT-4o mini API cost?

GPT-4o mini costs $0.15 per million input tokens and $0.6 per million output tokens, with cached input at $0.075 per million (50% off).

How much does a typical chat message cost with GPT-4o mini?

A short chat message (about 500 input and 250 output tokens) costs roughly $0.0002 with GPT-4o mini. At 1,000 such requests a day, that is about $6.75 per month.

Is GPT-4o mini cheap compared to similar models?

GPT-4o mini has the #4 cheapest input rate of the 26 models we track. On a mixed workload (10K input / 2K output), it costs $0.0027 per request, versus $0.0018 for Gemini 2.5 Flash-Lite.

Related

Compare all models at once ·Count tokens in your prompt

Last updated 2026-08-03. Prices verified againstOpenAI's official pricing page; see themethodology.