Ministral 3B

Ministral 3B is Mistral's smallest production model, a 3B parameter edge-optimized architecture that benchmarks above the larger Mistral 7B at $0.1 per million input tokens. Your use is subject to Mistral's Terms & Privacy Policies.

Tool UseVision (Image)

Use with AI Gateway View docs

import { streamText } from 'ai'

const result = streamText({
  model: 'mistral/ministral-3b',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview API About Providers Throughput Latency Uptime Status Similar FAQ

Copy link to headingMore models by Mistral

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Release Date

mistral/devstral-small-2

256K

0.4s

68tps

$0.10/M

$0.30/M

—

12/09/2025

mistral/mistral-large-3

256K

0.6s

52tps

$0.50/M

$1.50/M

—

12/02/2025

mistral/ministral-14b

256K

0.4s

93tps

$0.20/M

—

12/02/2025

mistral/mistral-small

32K

0.5s

195tps

$0.10/M

$0.30/M

—

09/17/2024

mistral/mistral-nemo

131K

0.3s

126tps

$0.15/M

—

07/18/2024

mistral/mistral-embed

$0.10/M

—

12/11/2023

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Ministral 3B

Copy link to headingMore models by Mistral