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.

Sonar Pro SearchPerplexity Remove
Gemini 4 ArgonGoogle Remove
Muse Spark OpenMeta Remove

Add a model

Kimi K3.1 Pro
DeepSeek V4.1 Flash 1017
Nemotron 3.5 Super VL (Free)
Nemotron 3.5 Super VL
Muse Wonder
Gemini 3.1 Flash Lite Image (Google Vertex AI)
Gemini 3.1 Flash Lite Image (Google AI Studio)Enterprise & partner access
Gemini 3.1 Flash Image (Google Vertex AI)Enterprise & partner access

sonar-pro-search vs gemini-4-argon vs muse-spark-open
Attribute	Sonar Pro Searchsonar-pro-search	Gemini 4 Argongemini-4-argon	Muse Spark Openmuse-spark-open
Pricing
Input	$3.75 / 1M	$2.00 / 1M	$1.25 / 1M
Output	$18.75 / 1M	$10.00 / 1M	$4.25 / 1M
Cache Write (5m)	$3.75 / 1M	$2.00 / 1M	$1.25 / 1M
Cache Write (1h)	$3.75 / 1M	$2.00 / 1M	$1.25 / 1M
Cache Read	$3.75 / 1M	$2.00 / 1M	$1.25 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	200K	1M	1M
Max output	N/A	N/A	N/A
Capabilities
Vision	Yes	Yes	Yes
Function Calling	Yes	Yes	Yes
JSON Mode	Yes	Yes	Yes
Streaming	Yes	Yes	Yes
Catalogue
Provider	Perplexity	Google	Meta
Category	chat	chat	chat
Charge type	Pay As You Go	Pay As You Go	Pay As You Go
Released	—	—	—
Description
Summary	Sonar Pro Search is Perplexity's most advanced agentic search system, available only via OpenRouter. It powers the Pro Search mode on Perplexity, adding autonomous multi-step research workflows instead of single-query answers. Pricing combines token costs with a per-request fee.	Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.	Muse Spark Open is an open-weight, coding-optimized model designed for agentic software engineering workflows. It delivers strong first-attempt accuracy, reliable tool calling, and deep codebase understanding, enabling effective development across real-world repositories. Optimized for autonomous coding agents, complex code navigation, and tool-driven development, Muse Spark Open is well suited for software engineering automation, debugging, code generation, and multi-step coding workflows where accuracy and reliable execution are essential.