Perplexity has launched the BrowseSafe system, designed to protect AI browser proxies from being manipulated by online content in real time. The system claims a 91% success rate in detecting prompt injection attacks, which is higher than GPT-5's 85% and PromptGuard-2's 35%. Additionally, it runs quickly and can monitor in real time. As AI browser proxies become more widespread, such security solutions are becoming increasingly important.
Perplexity's free AI shopping assistant, now available in the U.S., refines product recommendations through user input and follow-up questions, offering personalized holiday shopping experiences similar to ChatGPT.....
OpenAI and Perplexity launch AI shopping assistants in chatbots, enabling product searches via text or images to compare prices, entering the trillion-dollar e-commerce market.....
Perplexity company launches a free AI tool called Perplexity Patents, aiming to simplify the patent search process. This tool integrates data from multiple patent platforms, helping users quickly access patent information and solve the cumbersome and time-consuming issues of traditional searches. It is currently in the testing phase and open for use by all users.
AI Fiesta is a platform that allows you to communicate with world - class AI models such as ChatGPT, Gemini Pro, Claude, Perplexity, Deepseek, and Grok.
An open-source AI search engine framework with performance comparable to Perplexity.ai Pro.
An AI Research Assistant to Boost Team Efficiency
Google
$0.7
Input tokens/M
$2.8
Output tokens/M
1k
Context Length
Anthropic
$7
$35
200
$2.1
$17.5
$21
$105
Alibaba
$6
$24
256
-
$15.8
$12.7
64
Bytedance
$0.8
$2
128
Xai
$1.4
$10.5
Baidu
Tencent
Openai
$8.75
$70
400
$525
$4
$16
DevQuasar
This project is a quantized version based on the MiniMaxAI/MiniMax-M2 model, aiming to make knowledge accessible to the public. It provides multiple model versions with different quantization levels and shows the perplexity performance indicators of each version.
ubergarm2
This is a collection of quantized versions of the inclusionAI/Ling-1T model, developed based on the ik_llama.cpp branch. It offers multiple quantization schemes to meet different memory and performance requirements. These quantized models provide excellent perplexity performance under a given memory footprint and are specifically optimized for the inference efficiency of the MoE architecture.
inferencerlabs
Kimi-K2 Dynamic MLX is a text generation project built on the moonshotai/Kimi-K2-Instruct model, using the optimized MLX library to achieve efficient quantization performance. This model runs on a single M3 Ultra machine with 512GB RAM, supports multiple quantization methods, and shows excellent perplexity metrics in tests.
ai-forever
This is a language model with 1.3 billion parameters specifically designed for Azerbaijani. It is fine-tuned based on the mGPT-XL architecture and can efficiently process Azerbaijani text, achieving a perplexity of 5.37 on the validation set.
nyu-mll
A RoBERTa base model pre-trained on 1B tokens with a validation perplexity of 3.93, suitable for English text processing tasks.
flboehm
A text processing model fine-tuned based on bert-base-uncased, trained on an unknown dataset, with a validation loss of 2.4969 and perplexity of 12.14
The Perplexity MCP Server is an intelligent research assistant that uses Perplexity's AI model to automatically analyze query complexity and select the best model to process requests. It supports three tools: search, reasoning, and in - depth research.
An MCP server based on the Perplexity AI API, providing web search functionality for the Claude desktop client.
The Perplexity MCP Server is an intelligent research assistant that uses Perplexity's AI model to provide automatic query complexity detection and optimal model routing functions, supporting three tools: search, reasoning, and in - depth research.
A simple MCP server based on Perplexity AI, providing web search functionality and supporting development and deployment in the Windows environment.
Perplexity Advanced MCP is an advanced integration package that provides enhanced query processing capabilities through OpenRouter and Perplexity API, supporting simple and complex queries, and optimizing cost and performance.
A research - level MCP server implementation that interacts with the Perplexity website without an API key, providing AI - driven research functions such as web search, document retrieval, API lookup, and code analysis.
Octagon Deep Research MCP provides AI-driven in-depth research and analysis services, integrates advanced research agents, has no rate limit, is faster than ChatGPT in-depth research, and is more comprehensive than Grok DeepSearch or Perplexity. It supports various MCP clients and is suitable for comprehensive research on any topic or industry.
OpenDeepSearch is an open - source research tool and an alternative to Perplexity Deep Research. It provides in - depth search and research capabilities through the Model Context Protocol (MCP). It can break down complex problems into sub - problems, perform multiple rounds of searches using the Brave Search API, analyze the results, and generate structured research reports. It supports citation of sources and can be integrated into MCP clients such as Claude Desktop and Cursor.
The MCP server for the Perplexity API, providing chat completion with references.
An intelligent research assistant integrating Perplexity AI, providing functions such as search, document retrieval, API discovery, and code modernization check, supporting context tracking and efficient API management.
An MCP server implementation integrating the Perplexity AI API, providing advanced search functions and multi - model support.
A model control protocol server that supports parallel queries from multiple LLM providers. It can simultaneously call the APIs of OpenAI, Anthropic, Perplexity, and Google for cross-verification, providing a unified interface and supporting asynchronous processing.
The Perplexity MCP Server is an intermediate server written in Go that provides AI assistants (such as Claude and Cursor) with seamless access to the Perplexity API, including real-time search and complex reasoning functions.
A code problem-solving service that combines various AI and community resources. By integrating the analyses of Gemini AI, Stack Overflow, and Perplexity AI, it provides developers with multi - perspective programming solutions.
Perplexity Deep Research MCP is a Model Context Protocol server that provides web search functionality for the Perplexity AI API, supporting AI assistants to perform web searches using the sonar - deep - research model.
The Perplexity MCP Server is a Node.js-based server that implements Anthropic's Model Context Protocol (MCP) for connecting Claude and Perplexity's language models, providing enhanced AI interaction tools.
An intelligent code analysis and debugging server based on the Perplexity AI API, seamlessly integrated with the Claude desktop client, providing error analysis, pattern recognition and solution recommendations.
An MCP server based on the Perplexity API that provides web search functionality for AI assistants, supporting time filtering and result citation.
An intelligent code analysis and debugging service based on the Perplexity AI API, integrated with the Claude desktop client through the MCP protocol, providing functions such as error analysis, pattern recognition, and solution recommendation.
An MCP server based on TypeScript, providing tools for interacting with the Perplexity AI API, supporting search - enhanced queries and displaying internal reasoning processes.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
