Skip to content

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. Muse Spark 1.3MetaRemove
  3. Voxtral Small 24B 2507 STTMistral AIRemove
qwen3-asr-0.6b vs muse-spark-1.3 vs voxtral-small-24b-2507-stt
AttributeQwen3 ASR 0.6Bqwen3-asr-0.6bMuse Spark 1.3muse-spark-1.3Voxtral Small 24B 2507 STTvoxtral-small-24b-2507-stt
Pricing
Input$0 / 1M$1.25 / 1M$0 / 1M
Output$0 / 1M$4.25 / 1M$0 / 1M
Cache Write (5m)Not applicable$1.25 / 1MNot applicable
Cache Write (1h)Not applicable$1.25 / 1MNot applicable
Cache ReadNot applicable$1.25 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/A1MN/A
Max outputN/AN/AN/A
Capabilities
VisionNoYesNo
Function CallingNoYesNo
JSON ModeNoYesNo
StreamingNoYesNo
Catalogue
ProviderQwenMetaMistral AI
Categoryvoicechatvoice
Charge typePay As You GoPay As You GoPay As You Go
Released2026-08-13—2026-08-13
Description
SummaryQwen3-ASR 0.6B 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.Mistral AI Voxtral Small (24B) speech-to-text. Billed per second of audio.