Skip to content
Apertis

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Voxtral Mini 3B 2507Mistral AIRemove
  2. Voxtral Small 24B 2507 STTMistral AIRemove
  3. Perceptron Mk1.5PerceptronRemove
voxtral-mini-3b-2507 vs voxtral-small-24b-2507-stt vs perceptron-mk1.5
AttributeVoxtral Mini 3B 2507voxtral-mini-3b-2507Voxtral Small 24B 2507 STTvoxtral-small-24b-2507-sttPerceptron Mk1.5perceptron-mk1.5
Pricing
Input$0 / 1M$0 / 1M$0.15 / 1M
Output$0 / 1M$0 / 1M$1.50 / 1M
Cache Write (5m)Not applicableNot applicable$0.15 / 1M
Cache Write (1h)Not applicableNot applicable$0.15 / 1M
Cache ReadNot applicableNot applicable$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A36.9K
Max outputN/AN/AN/A
Capabilities
VisionNoNoNo
Function CallingNoNoNo
JSON ModeNoNoNo
StreamingNoNoYes
Catalogue
ProviderMistral AIMistral AIPerceptron
Categoryvoicevoicechat
Charge typePay As You GoPay As You GoPay As You Go
Released2026-08-132026-08-132026-09-25
Description
SummaryMistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.Mistral AI Voxtral Small (24B) speech-to-text. Billed per second of audio.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.