Skip to content
LLMs
Mistral AI logo

Mistral: Mistral Small 3.2 24B

by Mistral AI

Mistral: Mistral Small 3.2 24B is a large language model from Mistral AI. It costs $0.075 per million input tokens and $0.200 per million output tokens. Its context window is 256K tokens.

Tool callingStructured outputOpen weightsimage input
Input / 1M tokens
$0.075
Output / 1M tokens
$0.200
Cached input / 1M
-

Not supported

Context window
256K

tokens

Who serves it cheapest

3 hosts serve Mistral Small 3.2 24B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Mistral: Mistral Small 3.2 24B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DeepInfraCheapestfp8$0.075$0.200128K-99.7%
Venicefp8$0.094$0.250256K-99.7%
Parasailbf16$0.090$0.300131K-99.9%

The spread between DeepInfra and Parasail is 1.3× for identical weights. Quantization and context limits differ, so check both columns before switching.

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...

Specifications

Mistral: Mistral Small 3.2 24B specifications
Model IDmistralai/mistral-small-3.2-24b-instruct
ProviderMistral AI
Context window256K tokens
Max output16K tokens
Input modalitiesimage, text
Output modalitiestext
Knowledge cutoff2023-10-31
Open weightsYes - mistralai/Mistral-Small-3.2-24B-Instruct-2506
ReleasedJune 20, 2025

Cheaper alternatives

Models that cost less than Mistral Small 3.2 24B while keeping at least half its context window and every input modality it supports.

Nova Lite 1.0

$0.060 in · $0.240 out

about the same cheaper

Ministral 3 3B 2512

$0.100 in · $0.100 out

1.1× cheaper

Ling 3.0 Flash VL

$0.060 in · $0.180 out

1.2× cheaper

Gemma 3 12B

$0.050 in · $0.150 out

1.4× cheaper

Gemma 3 4B

$0.050 in · $0.100 out

1.7× cheaper

Frequently asked

How much does Mistral: Mistral Small 3.2 24B cost?

$0.075 per million input tokens and $0.200 per million output tokens.

What is the context window of Mistral: Mistral Small 3.2 24B?

256K tokens, with up to 16K tokens of output per request.

Which provider serves Mistral: Mistral Small 3.2 24B cheapest?

DeepInfra at $0.075 per million input tokens - 1.3× cheaper than Parasail, the most expensive of the 3 hosts serving it.

Confirm against the source: Mistral AI official pricing.