Enterprise DNAEnterprise DNA
Mistral logo

Models · Best cheap

Mistral Small 3.2 24B

by Mistral

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.

Visit Mistral ↗

Our verdict

Not reviewed yet

We have not reviewed Mistral Small 3.2 24B yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Mistral Small 3.2 24B

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.

Best for

Cheap EU-friendly assistants and light coding

Use cases

  • support bots
  • classification
  • light coding

Enterprise DNA angle

Omni can pin EU workloads to Mistral Small while US workloads use other providers.

Notes

Mistral Small 3.2 24B is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Small, fast, EU-friendly option
  • Good enough for many assistant workloads

Cons

  • Not a frontier reasoning model
  • Smaller context than long-context flagships

Key facts

What we have checked

Input price
$0.100 per million tokens
Checked OpenRouter models API
Output price
$0.300 per million tokens
Checked OpenRouter models API
Price on deepinfra
$0.075 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$0.200 per million output tokens
Checked OpenRouter models API
Price on mistralai
$0.010 per million cached input tokens
Checked OpenRouter models API
Price on mistralai
$0.100 per million input tokens
Checked OpenRouter models API
Price on mistralai
$0.300 per million output tokens
Checked OpenRouter models API
Price on parasail
$0.050 per million cached input tokens
Checked OpenRouter models API
Price on parasail
$0.090 per million input tokens
Checked OpenRouter models API
Price on parasail
$0.300 per million output tokens
Checked OpenRouter models API
Price on venice
$0.094 per million input tokens
Checked OpenRouter models API
Price on venice
$0.250 per million output tokens
Checked OpenRouter models API

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `mistralai/mistral-small-3.2-24b-instruct`.

  • openrouter · mistralai/mistral-small-3.2-24b-instruct · Docs

OpenRouter id: mistralai/mistral-small-3.2-24b-instruct

Price

What Mistral Small 3.2 24B costs, over time

Input price

$0.075 to $0.100

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.200 to $0.300

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
deepinfraInput$0.075 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.200 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
mistralaiCached input$0.010 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
mistralaiInput$0.100 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
mistralaiOutput$0.300 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.090 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$0.300 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$0.094 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$0.250 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Mistral Small 3.2 24B is used

Tokens served a day

2.4B to 4.3B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Mistral Small 3.2 24B scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Design Arena rating (Elo)929EloAs of 10 Nov 2026Design Arena via OpenRouter

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 0.2 to 0.3

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.075 to 0.1

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 0.25 to 0.2

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.09375 to 0.075

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 0.2 to 0.25

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.075 to 0.0938

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 0.3 to 0.2

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.1 to 0.075

    Source: OpenRouter models API

  9. Price changed

    output per mtok: 0.2 to 0.3

    Source: OpenRouter models API

  10. Price changed

    input per mtok: 0.075 to 0.1

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Mistral Small 3.2 24B is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
26.2B ▼5.6%
Requests, last 7 days
11.2M
Tool calls, last 7 days
441K
Average cost per request
2.2¢
Price per million tokens
$0.1 in · $0.3 out
05B10B19 Sept: 2.4B tokens, 858K requests20 Sept: 2.4B tokens, 840K requests21 Sept: 3.4B tokens, 1.3M requests22 Sept: 3.1B tokens, 1.3M requests23 Sept: 3.2B tokens, 1.6M requests24 Sept: 3.2B tokens, 1.5M requests25 Sept: 3.3B tokens, 1.6M requests26 Sept: 2.5B tokens, 1.7M requests27 Sept: 2.7B tokens, 1.6M requests28 Sept: 3.8B tokens, 2.2M requests29 Sept: 5.3B tokens, 2.2M requests30 Sept: 4.2B tokens, 2.4M requests1 Oct: 5B tokens, 2.1M requests2 Oct: 4.7B tokens, 1.9M requests3 Oct: 4.2B tokens, 1.8M requests4 Oct: 4.4B tokens, 1.7M requests5 Oct: 3.7B tokens, 1.7M requests6 Oct: 5B tokens, 1.7M requests7 Oct: 5.7B tokens, 2M requests8 Oct: 5.9B tokens, 2.4M requests9 Oct: 6.8B tokens, 3.1M requests10 Oct: 5.4B tokens, 2.4M requests11 Oct: 4.7B tokens, 2.4M requests12 Oct: 6.6B tokens, 2.6M requests13 Oct: 5.5B tokens, 2M requests14 Oct: 6.4B tokens, 2.5M requests15 Oct: 5.4B tokens, 1.9M requests16 Oct: 6.5B tokens, 2.7M requests17 Oct: 4.5B tokens, 1.6M requests18 Oct: 3.5B tokens, 1.6M requests19 Oct: 3.5B tokens, 1.7M requests20 Oct: 3.6B tokens, 1.7M requests21 Oct: 3.7B tokens, 1.7M requests22 Oct: 3.5B tokens, 1.9M requests23 Oct: 3.5B tokens, 1.8M requests24 Oct: 3.3B tokens, 1.7M requests25 Oct: 3.9B tokens, 1.9M requests26 Oct: 4B tokens, 1.8M requests27 Oct: 4.4B tokens, 1.9M requests28 Oct: 4B tokens, 2.3M requests29 Oct: 4.1B tokens, 2M requests30 Oct: 3.9B tokens, 1.8M requests31 Oct: 3.8B tokens, 2.2M requests1 Nov: 3.9B tokens, 2.4M requests2 Nov: 3.8B tokens, 1.8M requests3 Nov: 4.2B tokens, 1.9M requests4 Nov: 3.5B tokens, 1.6M requests5 Nov: 4.1B tokens, 1.8M requests6 Nov: 3.8B tokens, 1.6M requests7 Nov: 3.3B tokens, 1.4M requests8 Nov: 3.6B tokens, 1.5M requests9 Nov: 3.6B tokens, 1.6M requests10 Nov: 4.3B tokens, 1.6M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Mistral Small 3.2 24B.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-09. Hosting routes and app features can differ.

DeveloperMistral
Exact model identifiermistralai/mistral-small-3.2-24b-instruct
Inputimage, text
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Apache 2.0, open weights
Context length
256K tokens
Knowledge cutoff
31 Oct 2023
Developer release date
Not established
First seen in the catalogue
20 Jun 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

mistralai/mistral-small-3.2-24b-instruct: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-09
openrouter.ai ↗

Source for first seen, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-09
Licence source ↗

Licence declared in the mistralai/Mistral-Small-3.2-24B-Instruct-2506 model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Design Arena: 929 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →