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.

4 is the maximum. Remove one to add another.

voxtral-mini-3b-2507 vs muse-spark-1.3 vs nova-3 vs aura-2
Attribute	Voxtral Mini 3B 2507voxtral-mini-3b-2507	Muse Spark 1.3muse-spark-1.3	Nova-3nova-3	Aura-2aura-2
Pricing
Input	$0 / 1M	$1.25 / 1M	$0 / 1M	$0 / 1M
Output	$0 / 1M	$4.25 / 1M	$0 / 1M	$0 / 1M
Cache Write (5m)	Not applicable	$1.25 / 1M	Not applicable	Not applicable
Cache Write (1h)	Not applicable	$1.25 / 1M	Not applicable	Not applicable
Cache Read	Not applicable	$1.25 / 1M	Not applicable	Not applicable
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	N/A	1M	N/A	N/A
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	No	Yes	No	No
Function Calling	No	Yes	No	No
JSON Mode	No	Yes	No	No
Streaming	No	Yes	No	No
Catalogue
Provider	Mistral AI	Meta	Deepgram	Deepgram
Category	voice	chat	voice	voice
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	2026-08-13	—	2026-07-15	2026-07-16
Description
Summary	Mistral AI Voxtral Mini (3B) 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.	Deepgram Nova-3 speech-to-text. Billed per second of audio.	Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.