Skip to main content
Mistral AI logo

Ministral 3 14B API pricing on Mistral AI

Every Mistral AI Ministral 3 14B rate we track, compared against 8 providers serving the same model.

Input from /1M
$0.200
Output /1M
$0.200
Input price rank
#2 of 8
Last updated
November 21, 2026

The cheapest Ministral 3 14B input price we currently track is $0.200/1M on Liquid Inference.

The cheapest Ministral 3 14B output price is $0.200/1M on Liquid Inference.

Mistral AI Ministral 3 14B rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Mistral AI Ministral 3 14B pricing by mode
ModeInputOutput
Standard$0.200/1M$0.200/1M

About Ministral 3 14B

Creator
Mistral
Context
128K
Modalities
text
Tool calling
Yes
Open weights
Yes
Full Ministral 3 14B details and every provider →Compare API pricing for every Mistral model →

Ministral 3 14B on other providers

About Mistral AI

Mistral AI is a Paris-based AI company building frontier open and commercial language models. They offer comprehensive AI solutions including inference APIs, developer tools (Studio), AI agents (Vibe), model training (Forge), and compute infrastructure, combining open-source leadership with commercial-grade enterprise solutions.

Frequently Asked Questions

How much does Ministral 3 14B cost on Mistral AI?

Mistral AI serves Ministral 3 14B from $0.200 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Mistral AI the cheapest way to run Ministral 3 14B?

Mistral AI ranks #2 of 8 providers we track serving Ministral 3 14B on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $0.200/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Mistral AI offer batch or cached pricing for Ministral 3 14B?

We track 1 Ministral 3 14B offering from Mistral AI. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.