Skip to main content

Mistral Small 3.2 24B 2506

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 WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks. It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).

Input / output price
$0.075 / $0.20 per 1M
Context
128K tokens
Released
Jun 20, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "mistral-small-3.2-24b-instruct-2506".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/mistral-small-3.2
$0.075/M$0.20/M

Pricing

USD per 1M tokens on Concentrate, after gateway discounts.

Input
$0.075 per 1M
Output
$0.20 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.075/MConcentrate

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

16tokens/sacross providers

Faster than 32% of the other 599 models on the gateway

Response latency

Lower is better

1.3sacross providers

Faster than 61% of the other 780 models on the gateway

Benchmarks

5 published scores from 1 source, each linked to where it was published.

Published scores

BenchmarkScore
GPQA Diamondhuggingface.co46.1%

Apps

Use Mistral Small 3.2 24B 2506 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Mistral Small 3.2 24B 2506 FAQ

Short answers, built from the data on this page.

Mistral Small 3.2 24B 2506 is a model from Mistral, released on Jun 20, 2025. 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 WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks. It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).

On the Respan gateway, Mistral Small 3.2 24B 2506 costs $0.075 per 1M input tokens and $0.20 per 1M output tokens on Concentrate, after gateway discounts.

Mistral Small 3.2 24B 2506 is served by Concentrate.

Mistral Small 3.2 24B 2506 accepts up to 128K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "mistral-small-3.2-24b-instruct-2506". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Mistral Small 3.2 24B 2506 has 5 published benchmark scores, including GPQA Diamond 46.1%, MMLU 80.5%, and MMMU 62.5%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.