Grok 3 Mini
xAI's compact Grok 3 Mini model for fast, low-cost inference on the first-party API.
Source: xAI API docs, xAI console, Metadata verification, Field resolution verification
- Text
- Text
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate |
|---|---|
| Input | $0.3 / M |
| Output | $0.5 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Compare providers
The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.
| Platform | Region | Input / M | Output / M | Batch | Access |
|---|---|---|---|---|---|
xAILowest | - | $0.3 | $0.5 | - | First-party API |
Azure AI Foundry | - | $0.25 | $1.27 | - | Direct |
Azure AI Foundry · Data zone | - | $0.275 | $1.38 | - | Direct |
Azure AI Foundry · Regional | $0.275 | $1.38 | - | Direct |
Some hosts price by region. Shown rates match the selected region.
Price history
Has this model gotten cheaper or more expensive?
More from xAI (Grok)
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Grok 3 Mini call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.