Safeguard
Mistral AI logo

Mistral AI: Mistral Small 4

mistral/mistral-small-2603Available via Safeguard
Private cloudOn-prem

Use with Safeguard

Mistral Small 4 is available via Safeguard. Leave your work email and we will enable it for your workspace.

We will also add you to our newsletter; unsubscribe any time.

Released
March 16, 2026
Context
256,000 tokens
Input
$0.15 / 1M tokens
Output
$0.60 / 1M tokens

Overview

Hybrid model combining instruct, reasoning and coding in one model, with 119B total and 6.5B active parameters, Apache 2.0.

Provider
Mistral AI logoMistral AI
Modality
Text and image
Input
text, image
Output
text
Weights
Open weights
Supported parameters
tools, structured_outputs, reasoning, temperatureProvider's model page, checked .
Distillable
YesLicence or terms, checked .
Tags
open-weights, reasoning, coding, low-cost

Data policy

Prompts go to
Mistral AI (global endpoint by default)
Retention
Commercial terms: no training on customer data unless opted in, with exceptions, Studio Free mode may train on inputs and outputs (opt-out available), pay-as-you-go can opt out, ZDR available on pay-as-you-go for stateless endpoints
Zero data retention
Available
Region
Global by default, optional EU or US regional inference endpoints at 1.1x pricing

Summarised from the provider's published terms. The provider's own policy is what applies.

Where you can run it

How Mistral Small 4 can be deployed, bought and reached through Safeguard.

Deployment
Private cloudOn-prem
Procurement
Not published yet
Inference regions
Not published yet

On-prem deployments run wherever you install them.

Pricing

ProviderInput / 1M tokensOutput / 1M tokensContext
Mistral AI$0.15$0.60256K
Notes
Standard tier. Cached input $0.015.
Source
Mistral AI pricing , last verified October 27, 2026

No markup on model usage: you pay the provider's list price.

API

OpenAI-compatible. Your API key and access to this model are set up for your workspace when you choose Use with Safeguard.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.safeguard.sh/gpt/v1",
    api_key="SAFEGUARD_API_KEY",
)

response = client.chat.completions.create(
    model="mistral/mistral-small-2603",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/gpt/v1, model mistral/mistral-small-2603.

Self-healing security runs on Safeguard.

Your first fix PR is minutes away.

No sales call required, even your agent can complete the purchase over MCP.