LLMPrivate

Mistral Small 3.2 24B Instruct

Mistral's open-weight 24B instruction-tuned model with tool use, web search, and structured output — a production-ready upgrade to Small 3.1.

Get API key
Provider
Mistral AI
Price
$0.09 in · $0.25 out / 1M
Context window
256K tokens
Released
June 20, 2025
License
Apache 2.0

What is Mistral Small 3.2 24B Instruct?

Mistral Small 3.2 24B Instruct is a 24-billion-parameter language model released by Mistral AI in June 2025. It is an open-weight, Apache 2.0-licensed update to Small 3.1 with improved instruction following, reduced repetition, stronger function calling, and support for tool use and structured output.

Use it privately on Venice

On Venice, Mistral Small 3.2 runs with zero retention — your prompts are not stored, profiled, or used for training. It supports tool use, web search, and structured JSON output, giving you open-weight sovereignty and permissionless inference without Big-Tech surveillance. Per-token billing means you pay only for what you generate, with no subscription lock-in.

Private (zero retention)
No prompt training
TEE · hardware enclave
End-to-end encrypted

What can it do?

Strengths
  • Open weights under Apache 2.0 — self-host, fine-tune, or redistribute without licensing friction.
  • Major instruction-following upgrade over 3.1Arena Hard v2 rose to 43.1% and Wildbench v2 to 65.33%.
  • Production reliabilityinfinite-generation rate dropped to 1.29%, cutting repetition loops roughly in half.
  • Strong coding performance for its size — HumanEval Plus 92.90% and MBPP Plus 78.33%.
  • Native tool use and web search on Venice, plus structured JSON output for agent pipelines.
  • Extremely low inference cost on Venice — among the cheapest capable open-weight models available.
Limitations
  • General knowledge is solid but not frontier-level — MMLU sits at ~80.5% and MMLU-Pro at ~69%, behind larger flagship models.
  • 24B parameters means it can trail larger closed models on the hardest STEM and multi-step agentic tasks.
  • Not uncensored — it retains safety alignment and will refuse certain harmful requests.
  • It has no knowledge of events after its training data; use the built-in web search on Venice for real-time facts.
  • Runs quantized to fp8 on Venice, which trades a small amount of precision for speed and cost.

Mistral Small 3.2 24B Instruct capabilities

How to use it via API

Venice exposes an OpenAI-compatible API. Swap your base URL and call mistral-small-3-2-24b-instruct.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-small-3-2-24b-instruct",
    "messages": [{ "role": "user", "content": "Explain quantum tunneling simply." }]
  }'

Specifications

MakerMistral AI
ReleasedJune 20, 2025
ArchitectureDense transformer
Parameters24B
LicenseApache 2.0
Open weightsYes — downloadable from Hugging Face
Context window256K tokens
Max output16.384K tokens
CapabilitiesFunction calling, Web search
Privacy on VenicePrivate — zero retention
Available on Venice sinceJan 2026

Pricing

Billed per token on Venice: $0.09 per 1M input tokens and $0.25 per 1M output tokens.

Input / 1M tokens
$0.09
Output / 1M tokens
$0.25

New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.

Mistral Small 3.2 24B Instruct vs alternatives

ModelContext windowBest forOpen weightsPrice (Venice)
Mistral Small 3.2 24B Instruct256K tokensTool use & cost-efficient agentsYes$0.09 in · $0.25 out / 1M
DeepSeek V3.2160K tokensReasoning & STEMYes$0.33 in · $0.48 out / 1M
Google Gemma 4 31B Instruct256K tokensGeneral instruction & fine-tuningYes$0.12 in · $0.36 out / 1M
Kimi K2.6256K tokensLong-document analysisYes$0.75 in · $3.50 out / 1M

The best-value open-weight model for tool use and structured output under $0.30/1M tokens.

What is it good for?

  • Cost-efficient agents and tool-calling pipelines that need structured JSON output.
  • High-volume text classification, summarization, and data extraction.
  • Coding assistance and lightweight software engineering (HumanEval+ 92.90%).
  • Multilingual chat and content generation across 20+ languages.
  • Low-cost inference workloads where open-weight sovereignty is required.

Prompting tips

  • Be explicit and precise in prompts — the 3.2 update is specifically tuned for exact instruction following.
  • Use structured output schemas for reliable JSON extraction; the model supports schema constraints on Venice.
  • For coding tasks, provide clear function signatures and test cases to leverage its strong pass rates.
  • Enable web search when you need facts after the model's training cutoff instead of relying on parametric knowledge.
  • If you hit repetition, raise the temperature slightly or add a stop sequence — the model already reduces loops by default.

Version history

Mistral Small 3.1 24B Instruct
2025-03

Predecessor with the same base architecture.

Mistral Small 3.2 24B Instruct
2025-06

CurrentCurrent — improved instruction following, reduced repetition, and stronger function calling.

Frequently asked questions

It is a 24-billion-parameter dense language model released by Mistral AI in June 2025. It is an open-weight, Apache 2.0-licensed update to Small 3.1 with improved instruction following, reduced repetition, stronger function calling, and support for tool use and structured output.

Venice bills per token at $0.09 per 1M input tokens and $0.25 per 1M output tokens. There is no subscription required, and you can start with free credits.

Yes — the weights are released under Apache 2.0 on Hugging Face, so you can self-host, fine-tune, and redistribute them. Inference on Venice is private and permissionless.

Yes. On Venice it supports function calling, web search, and structured JSON output via schema constraints, making it suitable for agent pipelines.

Choose Mistral Small 3.2 for low-cost tool use, structured output, and high-volume agents. Choose DeepSeek V3.2 if you need stronger deep reasoning and coding performance and can pay roughly 3× the per-token cost.

No. It is open-weight but not uncensored — it retains safety alignment and will refuse certain harmful requests. Venice does not add extra content filters beyond the model's own weights.

It supports more than 20 languages including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, Arabic, Hindi, Bengali, and others.

It runs under Venice's private, zero-retention tier — prompts are not stored, profiled, or used for training. Venice does not run this model in a TEE or end-to-end encrypted session, but your data is not retained.

Related models

Run Mistral Small 3.2 24B Instruct privately.

No prompt logging. No data used for training. Free to start — no credit card.

Room