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 0.6BQwenRemove
  2. Gemini 3.5 TranscribeGoogleRemove
  3. Nova-3DeepgramRemove
  4. Muse Spark 1.3MetaRemove

4 is the maximum. Remove one to add another.

qwen3-asr-0.6b vs gemini-3.5-transcribe vs nova-3 vs muse-spark-1.3
AttributeQwen3 ASR 0.6Bqwen3-asr-0.6bGemini 3.5 Transcribegemini-3.5-transcribeNova-3nova-3Muse Spark 1.3muse-spark-1.3
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$1.25 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$4.25 / 1M
Cache Write (5m)Not applicableNot applicableNot applicable$1.25 / 1M
Cache Write (1h)Not applicableNot applicableNot applicable$1.25 / 1M
Cache ReadNot applicableNot applicableNot applicable$1.25 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/A98.3KN/A1M
Max outputN/AN/AN/AN/A
Capabilities
VisionNoYesNoYes
Function CallingNoYesNoYes
JSON ModeNoNoNoYes
StreamingNoNoNoYes
Catalogue
ProviderQwenGoogleDeepgramMeta
Categoryvoicevoicevoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-09-252026-07-15—
Description
SummaryQwen3-ASR 0.6B speech-to-text. Billed per second of audio.Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.Deepgram Nova-3 speech-to-text. Billed per second of audio.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.