XaiTool use

Grok 3 Mini pricing

A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible. Live index: 4 priced offers. Best input $0.250 per million tokens from Azure. Best output $0.500 per million tokens from Xai.

131K context·4 providers·save up to 17% vs native via Azure·verified Apr 7, 2026
Best input$0.250per 1M tokens · Azure
Best output$0.500per 1M tokens · Xai

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 4 offers are listed for Grok 3 Mini. Best input in this view: Azure.

X
Xainative
Input / 1M
$0.300
Output / 1M
$0.500
Cached in: $0.075
O
Openrouter
Input / 1M
$0.300
Output / 1M
$0.500
VA
Vercel Ai Gateway
Input / 1M
$0.300
Output / 1M
$0.500
A
Azure
Input / 1M
$0.250
Output / 1M
$1.27

Input vs output · per provider

Cost calculator

Use this block to stress test Grok 3 Mini cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.300/M·Out: $0.500/M·Cache: $0.075/M

0.030000¢ / req

0.025000¢ / req

Daily
$5.50
Monthly
$165
Annual
$2.0K

Model specifications

These fields describe Grok 3 Mini as we store it (source: Xai). They sit next to price so buyers can check limits and tools in one place.

Context window
131,072 tokens
Max output
131,072 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Jun 2025
Primary provider
Xai
Model family
N/A

Compare Grok 3 Mini

Open a pair page to see Grok 3 Mini next to another model with a shared provider matrix. 6 shortcuts below.

Frequently asked questions

Quick frequently asked items for Grok 3 Mini pricing and limits. The short model note from our index: A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

Grok 3 Mini costs $0.30 per million input tokens and $0.50 per million output tokens via the native API. Prompt caching reduces input costs to $0.07/M tokens.

Also from Xai

Other models by Xai with live pricing in our catalog.