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. Aura-2DeepgramRemove
  2. Perceptron Mk1.5PerceptronRemove
  3. Muse Spark 1.3MetaRemove
  4. Nova-3DeepgramRemove

4 is the maximum. Remove one to add another.

aura-2 vs perceptron-mk1.5 vs muse-spark-1.3 vs nova-3
AttributeAura-2aura-2Perceptron Mk1.5perceptron-mk1.5Muse Spark 1.3muse-spark-1.3Nova-3nova-3
Pricing
Input$0 / 1M$0.15 / 1M$1.25 / 1M$0 / 1M
Output$0 / 1M$1.50 / 1M$4.25 / 1M$0 / 1M
Cache Write (5m)Not applicable$0.15 / 1M$1.25 / 1MNot applicable
Cache Write (1h)Not applicable$0.15 / 1M$1.25 / 1MNot applicable
Cache ReadNot applicable$0.15 / 1M$1.25 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/A36.9K1MN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesNo
Function CallingNoNoYesNo
JSON ModeNoNoYesNo
StreamingNoYesYesNo
Catalogue
ProviderDeepgramPerceptronMetaDeepgram
Categoryvoicechatchatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-162026-09-25—2026-07-15
Description
SummaryDeepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Muse Spark 1.3 is Meta's multimodal reasoning model designed for long-running agentic, multi-agent, and coding workflows. It maintains context and information across extended tasks, enabling reliable execution in complex, multi-step environments. The model is optimized to resolve conflicting information, seek clarification or confirmation when necessary, and execute concisely, making it well suited for autonomous agents, collaborative multi-agent systems, and long-horizon software engineering workflows.Deepgram Nova-3 speech-to-text. Billed per second of audio.