Mistral: Mistral Small 3

24B

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.

Context
33K
Max output
16K
Input price
$0.05/1M tokens
Output price
$0.08/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode

Details

Model IDmistralai/mistral-small-24b-instruct-2501
Provider OpenRouter
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters24B
Architecture—
Context window33K tokens
Max input—
Max output16K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.05
Output
$0.08
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: mistral-small

ModelContextMax outPricing
Mistral: Mistral Small 3.1 24B (free)128K——
Mistral: Mistral Small 333K16K$0.05$0.08
Mistral: Mistral Small 4 (batch)262K210K$0.08$0.3
Mistral: Mistral Small 3.2 24B256K16K$0.08$0.2
Mistral: Mistral Small Creative33K—$0.1$0.3
Mistral: Mistral Small 4262K210K$0.15$0.6
Mistral: Mistral Small 3.1 24B128K102K$0.35$0.56

API

GET/v1/models/openrouter/mistralai/mistral-small-24b-instruct-2501

Mistral: Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.

Changes · 4 entries
mistralai/mistral-small-24b-instruct-2501update1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
mistralai/mistral-small-24b-instruct-2501update2b100acMar 23, 2026, 05:30 AM
parameters24
release_date2025-01-30
aliasmistralai/mistral-small-24b-instruct
taglineMistral Small 3 is a 24B-parameter language model optimiz...
tools["function_calling"]
mistralai/mistral-small-24b-instruct-2501update7a4f1f6Mar 22, 2026, 05:43 AM
model_typechat
mistralai/mistral-small-24b-instruct-2501create7f5c66fMar 21, 2026, 05:16 AM