Mistral Small 3.2 24B

by Mistralmistralai/mistral-small-3.2-24b-instruct

  • Text
  • No route yet
  • Released
  • Knowledge cutoff 31 October 2023

LLMCompare cannot run Mistral Small 3.2 24B yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.

See the models that can be run now

Mistral Small 3.2 24B at a glance

Context length
256,000 tokens
Maximum output
16,384 tokens
Accepts
Text, Image
Returns
Text
Features
JSON outputTool callingImage input
Reasoning effort levels
Not supported
Released
20 Jun 2025
Knowledge cutoff
31 October 2023

Model facts synced from the OpenRouter model list on 21 Oct 2026.

Mistral Small 3.2 24B pricing by route

A route is the service LLMCompare calls to reach the model. Mistral Small 3.2 24B has 1 route. Prices are in US dollars.

Prices of Mistral Small 3.2 24B on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$0.0938$0.25openrouter.ai/mistralai/mistral-small-3.2-24b-instruct

The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.

Cost calculator

Estimate what a batch of calls to Mistral Small 3.2 24B costs. The starting numbers are examples. Change them to match your task.

Cost per call
$0.00022
1 credits
Cost of 100 calls
$0.0219
100 credits

Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.

Parameters you can set

These are the parameters LLMCompare can set when it calls the model through OpenRouter.

Parameters of Mistral Small 3.2 24B
ParameterTypeRange or optionsDefault
temperatureNumber0 to 2in steps of 0.1Provider default
top_pNumber0 to 1in steps of 0.05Provider default
max_tokensInteger1 to 16,384Provider default
seedInteger-2,147,483,648 to 4,294,967,295Provider default
response_formatOne oftextjson_objectProvider default

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

Description as published for this model. LLMCompare has not edited it.

Models to compare with Mistral Small 3.2 24B

Text models from the same provider and models at the nearest price. The order is not a ranking.

Models to compare with Mistral Small 3.2 24B
Add to comparisonModelContextMax outputInput priceper 1M tokensOutput priceper 1M tokensFeaturesReleasedOn LLMCompare
Ministral 3 8B 2512Mistralmistralai/ministral-8b-2512262k210k$0.15$0.15JSONToolsCacheVisionNo route yet
Ministral 3 14B 2512Mistralmistralai/ministral-14b-2512262k210k$0.20$0.20JSONToolsCacheVisionNo route yet
Voxtral Small 24B 2507Mistralmistralai/voxtral-small-24b-250732.8k26.2k$0.10$0.30JSONToolsCacheNo route yet
Qwen3 Coder 30B A3B InstructQwenqwen/qwen3-coder-30b-a3b-instruct262k236k$0.07$0.28JSONToolsNo route yet
Llama Guard 4 12BMetameta-llama/llama-guard-4-12b164k16.4k$0.18$0.18VisionNo route yet
Qwen3 14BQwenqwen/qwen3-14b41k16.4k$0.12$0.24JSONToolsNo route yet

Questions about Mistral Small 3.2 24B

How much does Mistral Small 3.2 24B cost?
On the OpenRouter route, Mistral Small 3.2 24B costs $0.0938 per 1 million input tokens and $0.25 per 1 million output tokens, in US dollars. LLMCompare verified this price on 21 Oct 2026.
What is the context length of Mistral Small 3.2 24B?
Mistral Small 3.2 24B has a context length of 256,000 tokens and returns up to 16,384 output tokens in one call.
What inputs does Mistral Small 3.2 24B accept?
Mistral Small 3.2 24B accepts these inputs: Text, Image. Mistral Small 3.2 24B returns: Text.
Can I test Mistral Small 3.2 24B on my own data?
Not yet. LLMCompare lists the prices and parameters of Mistral Small 3.2 24B, but no route to Mistral Small 3.2 24B is configured on LLMCompare, so it cannot be selected for an evaluation.