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.

Muse Spark 1.3Meta Remove
Nova-3Deepgram Remove
Perceptron Mk1.5Perceptron Remove
DeepSeek V4.1 FlashDeepSeek Remove

4 is the maximum. Remove one to add another.

muse-spark-1.3 vs nova-3 vs perceptron-mk1.5 vs deepseek-v4.1-flash
Attribute	Muse Spark 1.3muse-spark-1.3	Nova-3nova-3	Perceptron Mk1.5perceptron-mk1.5	DeepSeek V4.1 Flashdeepseek-v4.1-flash
Pricing
Input	$1.25 / 1M	$0 / 1M	$0.15 / 1M	$0.30 / 1M
Output	$4.25 / 1M	$0 / 1M	$1.50 / 1M	$1.20 / 1M
Cache Write (5m)	$1.25 / 1M	Not applicable	$0.15 / 1M	$0.30 / 1M
Cache Write (1h)	$1.25 / 1M	Not applicable	$0.15 / 1M	$0.30 / 1M
Cache Read	$1.25 / 1M	Not applicable	$0.15 / 1M	$0.30 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	1M	N/A	36.9K	1M
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	No	No	Yes
Function Calling	Yes	No	No	Yes
JSON Mode	Yes	No	No	Yes
Streaming	Yes	No	Yes	Yes
Catalogue
Provider	Meta	Deepgram	Perceptron	DeepSeek
Category	chat	voice	chat	chat
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	—	2026-07-15	2026-09-25	—
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.	Deepgram Nova-3 speech-to-text. Billed per second of audio.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.	DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion.