MongoDB - Build AI That Scales
Mini tools| Model | Input | Cached input | Output | Unit |
|---|---|---|---|---|
|
Codestral 25.01
Mistral AI
|
$0.3 | - | $0.9 | per 1M tokens |
|
Devstral 2
Mistral AI
|
$0.4 | - | $2 | per 1M tokens |
|
Magistral Medium
Mistral AI
|
$2 | - | $5 | per 1M tokens |
|
Magistral Small
This model
Mistral AI
|
$0.5 | - | $1.5 | per 1M tokens |
|
Ministral 3 14B
Mistral AI
|
$0.2 | - | $0.2 | per 1M tokens |
|
Ministral 3 3B
Mistral AI
|
$0.1 | - | $0.1 | per 1M tokens |
|
Ministral 3 8B
Mistral AI
|
$0.15 | - | $0.15 | per 1M tokens |
|
Mistral Large 3
Mistral AI
|
$0.5 | - | $1.5 | per 1M tokens |
|
Mistral Medium 3.5
Mistral AI
|
$1.5 | - | $7.5 | per 1M tokens |
|
Mistral NeMo
Mistral AI
|
$0.15 | - | $0.15 | per 1M tokens |
|
Mistral Small 4
Mistral AI
|
$0.1 | - | $0.3 | per 1M tokens |
|
Mixtral 8x22B
Mistral AI
|
$2 | - | $6 | per 1M tokens |
|
Voxtral Small & Voxtral Mini
Mistral AI
|
$0.1 | - | $0.4 | per 1M tokens |
Magistral Small
By Mistral AI
Model family: Mistral
Magistral Small is designed as the lightweight sibling in Mistral’s “Magistral” family of models. With a reduced parameter count compared to larger versions, it trades some raw depth for faster responses, lower latency, and a smaller compute footprint. This makes it highly practical for deployments where speed and cost control are critical—such as customer support bots, lightweight assistants, and background automation.
The model still follows instructions precisely and generates structured outputs, so it integrates cleanly into agent frameworks, retrieval-augmented generation pipelines, and business process automations. It supports long-context handling for multi-document workflows, basic reasoning for analysis tasks, and coding assistance for everyday software work. Quantization and parameter-efficient tuning methods (like LoRA) make it easy to adapt Magistral Small to domain-specific needs without heavy infrastructure.
In practice, teams use it as the everyday backbone for assistants and copilots that need to be responsive and affordable, while reserving larger Magistral models for the most demanding reasoning or creative tasks.
The model still follows instructions precisely and generates structured outputs, so it integrates cleanly into agent frameworks, retrieval-augmented generation pipelines, and business process automations. It supports long-context handling for multi-document workflows, basic reasoning for analysis tasks, and coding assistance for everyday software work. Quantization and parameter-efficient tuning methods (like LoRA) make it easy to adapt Magistral Small to domain-specific needs without heavy infrastructure.
In practice, teams use it as the everyday backbone for assistants and copilots that need to be responsive and affordable, while reserving larger Magistral models for the most demanding reasoning or creative tasks.
Text
Gen 7
Overview
Magistral Small is a compact model from Mistral’s specialized lineup, tuned for efficiency while still offering solid reasoning and coding capabilities. At a smaller footprint, it delivers quick instruction following, structured JSON outputs, and function/tool calling support—making it ideal for cost-sensitive, real-time copilots and automations.
Pricing
Compare Magistral Small with other models listed in the same vendor pricing tiers and context lengths.
Standard
About Mistral AI
Mistral AI is a company that specializes in artificial intelligence and machine learning solutions.
View Company ProfileTools using Magistral Small
-
Juju🙏 95 karmaSep 11, 2024@Cabina.AIPersonal top 5 most convenient tools for creating content for website or social media. Writing text and generating images immediately -
I just used for a couple of scientific tasks and its output was as good as ChatGPT 4 and Gemini Pro. This is an interesting tool and I will be exploring it further
Last updated: April 6, 2026
