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. Nova-3DeepgramRemove
  2. Aura-2DeepgramRemove
  3. Qwen3 ASR 1.7BQwenRemove
  4. Voxtral Mini 3B 2507Mistral AIRemove

4 is the maximum. Remove one to add another.

nova-3 vs aura-2 vs qwen3-asr-1.7b vs voxtral-mini-3b-2507
AttributeNova-3nova-3Aura-2aura-2Qwen3 ASR 1.7Bqwen3-asr-1.7bVoxtral Mini 3B 2507voxtral-mini-3b-2507
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Cache Write (5m)Not applicableNot applicableNot applicableNot applicable
Cache Write (1h)Not applicableNot applicableNot applicableNot applicable
Cache ReadNot applicableNot applicableNot applicableNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/AN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoNo
Catalogue
ProviderDeepgramDeepgramQwenMistral AI
Categoryvoicevoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-152026-07-162026-08-132026-08-13
Description
SummaryDeepgram Nova-3 speech-to-text. Billed per second of audio.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.Qwen3-ASR 1.7B speech-to-text. Billed per second of audio.Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.