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. S1Fish AudioRemove
  2. Nemotron 3.5 ASR Streaming Multilingual 0.6BNVIDIARemove
  3. Perceptron Mk1.5PerceptronRemove
s1 vs nemotron-3.5-asr-streaming-multilingual-0.6b vs perceptron-mk1.5
AttributeS1s1Nemotron 3.5 ASR Streaming Multilingual 0.6Bnemotron-3.5-asr-streaming-multilingual-0.6bPerceptron 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
ProviderFish AudioNVIDIAPerceptron
Categoryvoicevoicechat
Charge typePay As You GoPay As You GoPay As You Go
Released2026-07-292026-08-132026-09-25
Description
SummaryFish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.NVIDIA Nemotron 3.5 ASR multilingual speech-to-text (0.6B). Billed per second of audio.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.