Mistral Small 3.2 24B — Mistral AI | Modeldex

Mistral Small 3.2 24B

Active

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. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Updated 4 days agoStructured data from Modeldex catalog

VisionBudget

Knowledge cutoff

Oct 31, 2023(2.5 years ago)

API release

Jun 20, 2025(10 months ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

History

Mistral Small 3.2 24B became available via the Mistral AI API on 2025-06-20.

Training & availability

Training data has a knowledge cutoff of 2023-10-31 — information about events after that date is unlikely to appear in the model's responses. Mistral AI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 128K tokens.
Input modalities: image, text.

Recommended for: vision, cheap.

Limitations

The knowledge cutoff is 30 months old — this model will not know about recent events, releases, or API changes.

Pricing

Input: $0.0750 per 1M tokens
Output: $0.2000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="mistral/mistral-small-3-2-24b-instruct",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.075/1M

Output tokens / month2.0M

@ $0.2/1M

Input cost

$0.375

5.0M × $0.075/1M

Output cost

$0.4

2.0M × $0.2/1M

Total / month

$0.775

$9.3 / year

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

1.1M/ month

HuggingFace likes

579

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.