Perplexity

GLM-5.2 added Perplexity Agent API, Droid, and more hosting options, while Baseten reported over 280 TPS and sub-0.8s TTFT. Builders should watch the cost and benchmark data as it moves into production agent stacks.

Perplexity said Computer will split tasks between on-device models and frontier cloud models, keeping some data on the local machine while escalating harder work remotely. That matters for privacy-sensitive workflows and for reducing token-heavy cloud usage on laptop-class hardware.

Perplexity replaced one-shot search calls with Search as Code, a Python-based search runtime in its Agent API that is also now the default in Computer. The change matters because agents can batch, rank, filter, and aggregate search steps inside code, and Perplexity says the system scored 0.386 on WANDR versus 0.152 for the next system.

Perplexity open-sourced the XLM-RoBERTa Unigram tokenizer it rebuilt for ranking and retrieval, reporting 5-6x lower CPU use and 63 microsecond p50 at 514 tokens. Teams running fast rerankers and embedders should watch tokenization cost as a latency bottleneck.

Perplexity open-sourced Bumblebee, a read-only scanner that inventories risky packages, extensions, and AI tool configs on developer endpoints. It covers 8+ package ecosystems plus MCP server configs, so teams can audit exposure before code reaches production.

Perplexity published serving results for post-trained Qwen3 235B on NVIDIA GB200 NVL72 and argues Blackwell materially outperforms Hopper for large MoE inference. The deltas show up in NVLS all-reduce latency, MoE prefill combine time, and high-speed decode throughput.

Perplexity published its internal manual for building agent skills and paired it with a research post about how those skills power products like Computer. The guide matters because it gives external builders concrete patterns for decomposing agent behavior into reusable skill folders instead of one-off prompts.

Perplexity released a new Mac app centered on Personal Computer, a local-first agent that works across local files, native Mac apps, and the web. It also supports remote control from iPhone and an always-on Mac mini setup paired with Comet.

Perplexity added Finance Search to the Agent API with licensed real-time market data and cited web sources in one tool call. The company says it led FinSearchComp T1 on live-data accuracy and lowest cost per correct answer, so teams building finance agents should evaluate it against their current stack.

Perplexity Computer is now available through Microsoft Teams and the Microsoft Marketplace, bringing its research and document workflows into workspace chat. The integration extends Computer from standalone use into enterprise collaboration surfaces.

OpenAI added GPT-5.5 and GPT-5.5 Pro to the API and Playground with 1M context and Responses support. Partners including OpenRouter, Perplexity, GitHub Copilot, Vercel, Warp, and Devin rolled it out the same day, widening access beyond Codex.

A day after Kimi K2.6’s launch, providers and tools opened new access paths including temporary free use in Hermes and Cline plus availability on Replicate, Together, Perplexity, and Tinker. Engineers can test the open model across agent harnesses and hosted runtimes without standing up their own stack first.

Perplexity launched Personal Computer for Mac, giving its desktop agent access to local folders, native apps, and the browser from one orchestration layer. It also supports Mac mini setups controlled from iPhone, pushing the product toward an always-on desktop agent.