Mistral AI: Codestral

Overview

Code model for low-latency tasks such as fill-in-the-middle completion and code generation.

Provider

Mistral AI

Modality

Text

Input

text

Output

text

Weights

Closed

Supported parameters

tools, structured_outputsProvider's model page, checked October 8, 2026.

Tags

coding, fim

Docs

Provider documentation

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

Policy

Mistral AI data policy

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

Where you can run it

How Codestral can be deployed, bought and reached through Safeguard.

Deployment

Public cloudPrivate cloud

Procurement

Not published yet

Inference regions

Not published yet

Closed weights stay with the provider, so this model runs in the provider's cloud, never on-prem or air-gapped.

Pricing

Notes

Standard tier. Cached input $0.03.

Source

Mistral AI pricing , last verified October 8, 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/codestral-2508",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/gpt/v1, model mistral/codestral-2508.