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. Qwen3 ASR 1.7BQwenRemove
  2. S2 ProFish AudioRemove
  3. Muse Spark 1.3MetaRemove
  4. Gemini 3.5 TranscribeGoogleRemove

4 is the maximum. Remove one to add another.

qwen3-asr-1.7b vs s2-pro vs muse-spark-1.3 vs gemini-3.5-transcribe
AttributeQwen3 ASR 1.7Bqwen3-asr-1.7bS2 Pros2-proMuse Spark 1.3muse-spark-1.3Gemini 3.5 Transcribegemini-3.5-transcribe
Pricing
Input$0 / 1M$0 / 1M$1.25 / 1M$0 / 1M
Output$0 / 1M$0 / 1M$4.25 / 1M$0 / 1M
Cache Write (5m)Not applicableNot applicable$1.25 / 1MNot applicable
Cache Write (1h)Not applicableNot applicable$1.25 / 1MNot applicable
Cache ReadNot applicableNot applicable$1.25 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A1M98.3K
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesYes
Function CallingNoNoYesYes
JSON ModeNoNoYesNo
StreamingNoNoYesNo
Catalogue
ProviderQwenFish AudioMetaGoogle
Categoryvoicevoicechatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-07-29—2026-09-25
Description
SummaryQwen3-ASR 1.7B speech-to-text. Billed per second of audio.Fish Audio S2 Pro text-to-speech. Billed per UTF-8 byte of input text.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.Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.