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.

DeepSeek V4.1 FlashDeepSeek Remove
Muse Spark 1.3Meta Remove
Perceptron Mk1.5Perceptron Remove
S1Fish Audio Remove

4 is the maximum. Remove one to add another.

deepseek-v4.1-flash vs muse-spark-1.3 vs perceptron-mk1.5 vs s1
Attribute	DeepSeek V4.1 Flashdeepseek-v4.1-flash	Muse Spark 1.3muse-spark-1.3	Perceptron Mk1.5perceptron-mk1.5	S1s1
Pricing
Input	$0.30 / 1M	$1.25 / 1M	$0.15 / 1M	$0 / 1M
Output	$1.20 / 1M	$4.25 / 1M	$1.50 / 1M	$0 / 1M
Cache Write (5m)	$0.30 / 1M	$1.25 / 1M	$0.15 / 1M	Not applicable
Cache Write (1h)	$0.30 / 1M	$1.25 / 1M	$0.15 / 1M	Not applicable
Cache Read	$0.30 / 1M	$1.25 / 1M	$0.15 / 1M	Not applicable
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	1M	1M	36.9K	N/A
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	Yes	No	No
Function Calling	Yes	Yes	No	No
JSON Mode	Yes	Yes	No	No
Streaming	Yes	Yes	Yes	No
Catalogue
Provider	DeepSeek	Meta	Perceptron	Fish Audio
Category	chat	chat	chat	voice
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	—	—	2026-09-25	2026-07-29
Description
Summary	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.	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.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.	Fish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.