The latest AI news and updates of Perplexity — an AI-powered answer engine delivering real-time, cited answers to any question. Covering Perplexity's latest product updates, launches, and research from the past 90 days.
PerplexitySep 10Perplexity updated its API MCP server to support OAuth authentication. Agents now connect by adding the server URL to a client, signing in with a Perplexity account, and approving the organization. This integration provides agents with real-time web search, deep research, and advanced reasoning capabilities, all powered by the underlying Agent API.
PerplexitySep 9Perplexity introduced Q2D-Web, a benchmark and public leaderboard for evaluating retrieval in agentic RAG systems. It features 190 million web documents and 69,721 agent-reformulated queries across ten languages. Initial results show pplx-embed-v1-4b leading Web Ranking and Combined metrics on Recall@1000, while Nemotron-3-Embed-8B leads in Citation-based retrieval.
PerplexitySep 9Perplexity integrated its Search API into the Hermes Agent platform, providing real-time web search results across an index of more than 400 billion URLs. The integration delivers relevance-ranked snippets directly within agent workflows. New accounts receive $10 in free API credits to begin building with the search-enabled agent backend.
PerplexitySep 5Perplexity published research on its in-house inference stack, Ivy, Tulip, and ROSE, which powers its embedding and ranking models. The infrastructure uses CUDA graphs, LazyTensors, and ragged attention to overlap CPU and GPU work. These optimizations reduce latency and improve throughput for both live-search and batch-indexing workloads, delivering faster search results at a lower cost than off-the-shelf solutions.
PerplexitySep 4Perplexity evaluated OpenAI's GPT-6 Astra on its WANDR benchmark, where it scored 0.682 at $11.98 per task. This result marks the highest score of any model tested. Compared to Fable 5.1, Astra scored 13.5% higher at 6.1% lower cost, and it outperformed Opus 5 by 27.0% at 3.3% higher cost.
PerplexitySep 3Perplexity has integrated its API into Stripe Projects, enabling terminal-based provisioning of API projects, keys, and prepaid credits. The flow supports auto-provisioning for new users and linking existing projects to maintain current billing. Provisioned keys provide access across the entire Perplexity API platform, including the Agent and Search APIs, with Stripe managing spend limits and key rotation.
PerplexitySep 2Perplexity open-sourced Lily, a local inference engine built for hybrid compute on Apple silicon. Specialized for Qwen3.6-35B-A3B, Lily maps model operations directly to hardware, achieving 1.23× higher prefill and 1.35× higher decode throughput than MLX-LM on an M5 Max MacBook Pro. The engine uses a Rust runtime and custom Metal kernels to minimize data movement during inference.
PerplexitySep 2Perplexity’s Agent API now supports 42 models, adding Z.AI’s open-weight GLM 5.3 reasoning model. Developers can now configure fallback chains to ensure high availability if a model becomes unavailable, and switch between models by changing a single request field. A new cookbook example demonstrates pairing GLM 5.3 with the people_search tool for customer record enrichment.
PerplexitySep 1Perplexity launched hybrid compute for its Mac app, splitting tasks between cloud models and a local model to keep sensitive data on-device. An on-device PII classifier detects personal information before it leaves the machine, ensuring sensitive steps remain local. This feature is available today for Pro, Max, and Enterprise subscribers on macOS 15+.
PerplexityAug 29Perplexity launched managed Connectors for its Agent API, providing integrations for GitHub, Slack, Google Drive, and Datadog. API Group admins connect each service once in the API Portal, allowing agents to reference them by ID without per-request tokens. The GitHub connector integrates with the Sandbox, enabling agents to clone private repositories, modify code, and open pull requests autonomously.
PerplexityAug 29Perplexity integrated Z.ai's GLM 5.3 into its Computer agent platform. Designed for long-context and multimodal workloads, the model scored 0.278 on Perplexity's WANDR benchmark, outperforming the previous GLM 5.2 version by 0.019 points. The model is available now for agentic research tasks.
PerplexityAug 26Perplexity updated Brain, its self-improving memory system for Computer, showing a 9.3-point gain in correctness, 8.0 in currentness, and 8.9 in recall while reducing token usage by 15%. Brain organizes context as a linked Markdown filesystem, using background Dream agents to synthesize information and verify claims through citation edges, ensuring agents maintain an accurate, navigable knowledge wiki.
PerplexityAug 25Perplexity launched Portable Computer, a fully local version of its agent platform running on NVIDIA DGX Spark. The system executes the orchestrator, subagents, and agent harness locally, eliminating cloud dependencies for on-device tasks. It supports PPLX 27B and Qwen 3.8 27B models, with user-gated cloud escalation to frontier models for complex tasks. Available today for Pro and Max subscribers.
PerplexityAug 22Perplexity released the Agent API, providing access to 41 frontier models across nine providers through a single endpoint. The API includes built-in tools for web search, finance search, URL fetching, and code execution. Presets range from fast to wide-research, supporting up to 100 steps. Pricing follows provider-direct rates with no markup, and tool fees apply only upon invocation.
PerplexityAug 22Perplexity released its API MCP server as an Agent Plugin 1.0.0 package. This portable format allows compatible clients like Cursor, Codex, and VS Code to install the server directly without per-client adaptation. The plugin provides agents with real-time web search, reasoning, and research capabilities through the Perplexity API.
PerplexityAug 22Perplexity integrated DeepSeek V4 Pro into its Computer agent platform with U.S. hosting. Internal WANDR benchmark evaluations show the model scoring 0.359 at $0.75 per task. This performance-to-cost ratio is 62 percent lower than the next model on the cost-performance frontier.
PerplexityAug 22Perplexity now enables Computer tasks directly through email. Sending, forwarding, or cc’ing computer@perplexity.com initiates a full Computer session, maintaining the same audit trail and memory as web-based tasks. The platform verifies sender permissions and returns deliverables as attachments, making the agent available to all Computer users today.
PerplexityAug 15Perplexity released an agent-first Python SDK that implements its Search as Code architecture. The SDK provides composable retrieval primitives, including ranking, filtering, and query fan-out, for direct orchestration by coding agents. It includes a dedicated pplx-search-sdk agent skill to integrate real-time web search and page snippets directly into agent workflows.
PerplexityAug 13Perplexity is migrating its Sonar model to the Agent API, which bundles multi-step research, code execution, and multi-model access into pre-configured presets. The new API outperforms Sonar models on BrowseComp and WideSearch benchmarks. Existing Sonar users have 45 days to migrate their integrations to the new platform.
PerplexityAug 13Perplexity integrated xAI’s Grok 4.6 into its answer engine and Perplexity Computer platform. On the WANDR benchmark, the model matches the performance of Anthropic’s Fable 5 while reducing task costs by over 60%. This addition provides a high-efficiency option for research and agentic workflows.
PerplexityAug 13Perplexity updated its Search as Code system, increasing WANDR benchmark scores by 9.2% while reducing per-task costs by 9.7%. Additionally, updates to the Search SDK within the Computer platform raised action execution reliability from 81.9% to 92.6%. These improvements enhance the efficiency and dependability of autonomous research workflows.
PerplexityAug 10Perplexity has integrated Moonshot AI’s Kimi K3 model into its Agent API, hosted exclusively on US-based servers. The integration supports long-horizon research and code execution, allowing agents to generate source-linked, interactive HTML data stories. The API combines live web search with K3’s reasoning capabilities to produce automated, inspectable reports.
PerplexityAug 8Perplexity integrated OpenAI’s GPT-5.6 Terra and Luna models into its Computer agent platform. Terra now serves as the default model for subagents and an orchestrator, while Luna handles scheduled automations. These models reduce subagent costs by 28 percent and automation costs by 72 percent, with Terra outperforming Claude Sonnet by 11 points on the WANDR benchmark.
PerplexityAug 5Perplexity has integrated Anthropic’s Claude Fable 5 into its Agent API, bundling the model with native search, retrieval, and code execution capabilities. The integration targets complex agent workflows, with pricing set at $10 per million input tokens and $50 per million output tokens. The API requires a max_output_tokens parameter for all Anthropic model requests.
PerplexityAug 3Perplexity released the pplx CLI, providing coding agents with direct access to live web search and query-relevant page snippets from the terminal. The tool supports automated web research and content extraction for non-interactive agent workflows. Agents authenticate using the PERPLEXITY_API_KEY, and the CLI outputs structured JSON data for integration into existing development environments.
PerplexityJul 30Perplexity launched Projects, an evolution of its Spaces feature, as a collaborative hub for ongoing work within its Computer agent platform. Projects provide a shared file system and persistent memory through Brain, where agents retain context across tasks and sessions. The update is available to all users today, supporting team collaboration and tool integration.
PerplexityJul 29Perplexity released Numbat, an open-source security suite for client-side AI agents. It provides live monitoring, pre-action blocking, and forensic reconstruction across agent harnesses on macOS, Linux, and Windows. Numbat uses 52 built-in rules to detect and prevent risky agent behavior, such as unauthorized secret access or privilege escalation, before actions execute. It ships as a single Go binary.
PerplexityJul 28Perplexity integrated Model Council into its Computer platform, enabling multi-model analysis for complex tasks. The tool evaluates a single issue across two to eight models from various providers. It synthesizes consensus, identifies disagreements, and generates work-ready assets like reports or decks based on the findings.
PerplexityJul 28Perplexity released Personal Computer for Windows, an always-on agent harness for Pro, Max, and Enterprise subscribers. The platform orchestrates 15+ models to perform tasks across local files, Microsoft 365 apps, and 400+ connected services. It features voice mode, Comet browser automation, and local folder access, allowing agents to read, edit, and manage work directly on the desktop.
PerplexityJul 25Perplexity added Anthropic’s Claude Opus 5 to its answer engine and Perplexity Computer platform. In internal WANDR benchmark evaluations, the model outperformed six other leading models, ranking second only to Fable 5. It delivers this performance at a 57% lower cost than Fable 5.
PerplexityJul 15Perplexity launched SPACE, a sandbox platform for long-running agentic workflows. SPACE provides secure, isolated environments for code execution and file management. It now powers 100% of Perplexity Computer traffic, reducing median sandbox creation latency from 185 milliseconds to 60 milliseconds and 90th-percentile latency from 447 milliseconds to 89 milliseconds.
PerplexityJul 14Perplexity open-sourced WANDR, an evaluation benchmark for research agents that must perform wide-and-deep knowledge work. The benchmark includes 500 realistic tasks requiring 170,495 source-backed records. WANDR grades agents by re-fetching cited pages and verifying claims against evidence, providing a dense signal to identify failures in discovery, enrichment, and factual accuracy across complex research hierarchies.
PerplexityJul 10Perplexity added xAI's Grok 4.5 as an orchestrator model for its Computer platform, available to Pro and Max subscribers. In WANDR benchmark evaluations, the model outperformed five other orchestrator configurations while costing roughly half as much as Opus 4.8.
PerplexityJul 10Perplexity launched Computer Analytics, a dashboard for tracking credit consumption across AI models. Located in Account Settings, the tool provides usage metrics for consumer and enterprise accounts. It displays total credits, active member counts, and a breakdown of consumption by model, including Claude and GPT variants, to provide visibility into agentic workflow costs.
PerplexityJul 10Perplexity added OpenAI’s GPT-5.6 Terra and Sol models to its answer engine and Perplexity Computer platform. The integration provides access to OpenAI’s latest flagship and balanced model variants directly within the interface.
PerplexityJul 9Perplexity released a research preview of a new orchestrator model for Perplexity Computer, adapted from GLM 5.2. The model features an advisor tool that natively escalates to stronger models when necessary. It delivers near-frontier performance at 0.344x the cost of Opus, averaging roughly half the cost of Opus across benchmarks while running on Nvidia B200 GPUs.
PerplexityJun 24Perplexity launched Computer for Counsel, a specialized version of its agentic platform designed to automate legal administrative tasks. The system connects to research databases, document tools, and matter-management systems like Midpage, LegalZoom, Docusign, and NetDocuments to pull citable sources for briefs and memos. It is available now for all Perplexity Pro and Max subscribers.
PerplexityJun 18Perplexity launched Brain, a self-improving memory system for its Computer agent platform. Brain builds a context graph of past work to refine future task execution, improving answer correctness by 25% and recall by 16% while reducing task costs by 13%. The system is available now as a research preview for all Perplexity Max subscribers.
Frequently asked questions