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.

muse-spark-1.3 vs voxtral-small-24b-2507-stt vs s1 vs nova-3
Attribute	Muse Spark 1.3muse-spark-1.3	Voxtral Small 24B 2507 STTvoxtral-small-24b-2507-stt	S1s1	Nova-3nova-3
Pricing
Input	$1.25 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Output	$4.25 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Cache Write (5m)	$1.25 / 1M	Not applicable	Not applicable	Not applicable
Cache Write (1h)	$1.25 / 1M	Not applicable	Not applicable	Not applicable
Cache Read	$1.25 / 1M	Not applicable	Not applicable	Not applicable
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	1M	N/A	N/A	N/A
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	No	No	No
Function Calling	Yes	No	No	No
JSON Mode	Yes	No	No	No
Streaming	Yes	No	No	No
Catalogue
Provider	Meta	Mistral AI	Fish Audio	Deepgram
Category	chat	voice	voice	voice
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	—	2026-08-13	2026-07-29	2026-07-15
Description
Summary	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.	Fish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.	Deepgram Nova-3 speech-to-text. Billed per second of audio.