OpenAIGPT-4VisionTool use

GPT-4o mini pricing

OpenAI's small, fast, affordable model for lightweight tasks. Below you will find 7 current rows with input and output dollars per million. Right now the lowest input is $0.150 and the lowest output is $0.600.

128K context·7 providers·verified Apr 7, 2026
Best input$0.150per 1M tokens · Vercel Ai Gateway
Best output$0.600per 1M tokens · Vercel Ai Gateway

Pricing across providers

Use this table to read GPT-4o mini list prices. We show 7 sources right now. Lowest input in the grid: Vercel Ai Gateway. The chart below the table helps when output prices are much higher than input prices.

GC
Github Copilot
Input / 1M
N/A
Output / 1M
N/A
VA
Vercel Ai Gateway
Input / 1M
$0.150
Output / 1M
$0.600
Cached in: $0.075
O
Openrouter
Input / 1M
$0.150
Output / 1M
$0.600
A
Azure
Input / 1M
$0.150
Output / 1M
$0.600
G
Gmi
Input / 1M
$0.150
Output / 1M
$0.600
R
Replicate
Input / 1M
$0.150
Output / 1M
$0.600
O
OpenAInative
Input / 1M
$0.150
Output / 1M
$0.600
Cached in: $0.075Batch: 50%

Input vs output · per provider

Cost calculator

Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for GPT-4o mini.

Provider

In: N/A/M·Out: N/A/M
Daily
$0.0000
Monthly
$0.0000
Annual
$0.0000
100% cheaper than the native API at this usage level

Model specifications

Quick spec sheet for GPT-4o mini before you dive back into pricing. Family: GPT-4. Reported under OpenAI.

Context window
128,000 tokens
Max output
16,384 tokens
Vision (images)
Yes
Tool / function calling
Yes
Streaming
Yes
Released
Jul 2024
Primary provider
OpenAI
Model family
GPT-4

Compare GPT-4o mini

Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for GPT-4o mini.

Frequently asked questions

Quick frequently asked items for GPT-4o mini pricing and limits. The short model note from our index: OpenAI's small, fast, affordable model for lightweight tasks.

GPT-4o mini costs $0.15 per million input tokens and $0.60 per million output tokens via the native API. Prompt caching reduces input costs to $0.07/M tokens. Batch API offers 50% off.

Also from OpenAI

Other models by OpenAI with live pricing in our catalog.