AI TOOLS RADAR
Submit
All models / MISTRALAI
mistralai logo
mistralai

Mistral: Mistral Small 3.2 24B

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
256,000 tokens
Maximum output
16,384 tokens
Architecture
text+image->text
Tokenizer
Mistral
Knowledge cutoff
2023-10-31
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.0938
per 1M tokens
Output
$0.25
per 1M tokens
API

Model configuration

Default parameters

temperature
0.3
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/mistral-small-3.2-24b-instruct","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
imagetext
Output
text
API

Supported API parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

3 providers

Checked: September 16, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

fp8
Context
128K
Maximum output
16K
Input
$0.075
Output
$0.2
Cache read
Not provided
Cache write
Not provided

Parasail

bf16
Context
131K
Maximum output
33K
Input
$0.09
Output
$0.3
Cache read
$0.05
Cache write
Not provided

Venice

fp8
Context
256K
Maximum output
16K
Input
$0.0938
Output
$0.25
Cache read
Not provided
Cache write
Not provided
mistralai

4 models

All models
mistralai logomistralai

Mistral: Voxtral Small 24B 2507 STT

Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.

Context
Not provided
Input
audio
Output
transcription
Audio seconds: $0.00005 per second
View model details →
mistralai logomistralai

Mistral: Voxtral Mini 3B 2507

Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.

Context
Not provided
Input
audio
Output
transcription
Audio seconds: $0.000017 per second
View model details →
mistralai logomistralai

Mistral: Voxtral Mini Transcribe

Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings,...

Context
Not provided
Input
audio
Output
transcription
Audio seconds: $0.00005 per second
View model details →
mistralai logomistralai

Mistral: Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Context
262K
Input
text · image · file
Output
text
Input: $1.5Output: $7.5per 1M tokens
View model details →