{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"perplexity-api","slug":"perplexity-api","name":"Perplexity API","type":"api","url":"https://docs.perplexity.ai","page_url":"https://unfragile.ai/perplexity-api","categories":["llm-apis"],"tags":[],"pricing":{"model":"usage","free":false,"starting_price":"$0.20/1M tokens"},"status":"active","verified":false},"capabilities":[{"id":"perplexity-api__cap_0","uri":"capability://text.generation.language.search.augmented.llm.inference.with.real.time.web.grounding","name":"search-augmented llm inference with real-time web grounding","description":"Perplexity's Sonar models integrate web search directly into the inference pipeline, automatically retrieving and ranking current web data during response generation. The API supports four model variants (Sonar, Sonar Pro, Sonar Reasoning Pro, Sonar Deep Research) with configurable search context depth (Low/Medium/High), enabling responses grounded in real-time information without requiring separate search orchestration. Search context size directly affects both latency and pricing, allowing builders to trade off comprehensiveness against cost.","intents":["I need LLM responses grounded in current web data without manually orchestrating search calls","I want to build a research assistant that cites sources and provides up-to-date information","I need to control the depth of web search (fast vs comprehensive) based on query complexity","I want to use reasoning-enhanced models that can search the web for multi-step problem solving"],"best_for":["teams building research assistants and fact-checking tools","developers creating real-time Q&A systems for current events or news","builders needing grounded responses without managing separate search infrastructure"],"limitations":["Search context depth (Low/Medium/High) is coarse-grained; no fine-grained control over search result count or ranking algorithm","Citation generation only available on Sonar Deep Research variant, not base Sonar models","Reasoning tokens (Sonar Reasoning Pro, Deep Research) add significant per-token cost ($3/1M for reasoning output)","No documented SLA for search freshness or latency impact of different context depths","Maximum input/output token limits not specified in documentation"],"requires":["API key from Perplexity (created via API Key Management dashboard)","HTTP client capable of POST requests with JSON payloads","Understanding of token-based pricing model (input, output, citation, reasoning tokens charged separately)"],"input_types":["text (natural language queries)","structured prompts with system instructions"],"output_types":["text (model response with inline citations for Deep Research variant)","structured metadata (citation sources, reasoning token counts)"],"categories":["text-generation-language","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_1","uri":"capability://text.generation.language.multi.provider.llm.access.with.integrated.web.search.tools","name":"multi-provider llm access with integrated web search tools","description":"The Agent API provides unified access to third-party LLM models (OpenAI, Anthropic, Google, xAI) through Perplexity's infrastructure, with two built-in web search tools (web_search and fetch_url) available as function calls. Builders invoke third-party models via a single API endpoint, and the models can autonomously call web_search ($0.005/invocation) or fetch_url ($0.0005/invocation) to retrieve current information. Pricing is transparent: model tokens charged at direct provider rates with no markup, plus separate tool invocation fees.","intents":["I want to use my preferred LLM (OpenAI, Claude, Gemini) but add web search capabilities without building my own search integration","I need to compare responses from multiple LLM providers while keeping search tools consistent","I want to let the model decide when to search the web vs use its training data, without manual tool orchestration","I need transparent pricing that separates model costs from tool invocation costs"],"best_for":["developers building multi-model LLM applications who want search without provider-specific integrations","teams evaluating different LLM providers while maintaining consistent search behavior","builders needing fine-grained cost tracking (model tokens vs tool invocations)"],"limitations":["Only two web tools available (web_search and fetch_url); no custom tool definitions or function calling beyond these two","Specific third-party model names/versions not documented; requires checking Agent API Models page for current availability","Tool invocation costs are additive and can accumulate quickly in agentic workflows (web_search at $0.005 per call)","No documented support for streaming or batch processing with Agent API","OpenAI Compatibility mode mentioned but details not provided; unclear which OpenAI features are supported"],"requires":["API key from Perplexity","No separate API keys for third-party providers required (Perplexity handles provider access)","Understanding of function calling semantics for the chosen LLM provider"],"input_types":["text (natural language prompts)","structured messages with system instructions","function calling schemas (for web_search and fetch_url)"],"output_types":["text (model response)","structured tool calls (web_search queries, fetch_url targets)","tool results (search results, fetched page content)"],"categories":["text-generation-language","tool-use-integration","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_10","uri":"capability://tool.use.integration.api.key.based.authentication.with.key.management.dashboard","name":"api key-based authentication with key management dashboard","description":"Perplexity API uses API key-based authentication where developers create and manage keys through the API Key Management dashboard. Keys are used in HTTP requests to authenticate API calls. The authentication mechanism is standard HTTP header-based (typical pattern: Authorization: Bearer <api_key>), enabling integration with standard HTTP clients and SDKs. Key management dashboard provides visibility into key creation, rotation, and usage.","intents":["I need to authenticate API requests without managing complex OAuth flows","I want to create and rotate API keys for different applications or environments","I need to track which keys are being used and revoke compromised keys","I want to implement API key-based access control for my application"],"best_for":["developers building simple integrations that don't require complex authentication","teams managing multiple applications or environments with separate API keys","builders needing straightforward key rotation and revocation"],"limitations":["API key authentication details not documented (header format, key format, expiration policy unknown)","No documented support for key expiration or automatic rotation","No documented support for scoped keys (all keys may have full API access)","No documented rate limiting per key or per application","Key management dashboard UI/UX not documented (unclear how to create, rotate, or revoke keys)"],"requires":["Perplexity account with API access enabled","Access to API Key Management dashboard","HTTP client capable of setting Authorization headers"],"input_types":["API key (created via dashboard)"],"output_types":["authentication token (used in HTTP requests)"],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_11","uri":"capability://tool.use.integration.perplexity.sdk.with.quickstart.guides.and.integration.documentation","name":"perplexity sdk with quickstart guides and integration documentation","description":"Perplexity provides an official SDK (language support not specified in documentation) with quickstart guides and integration documentation. The SDK abstracts HTTP request/response handling and provides language-native interfaces for API calls. SDK documentation includes guides for common use cases (e.g., building search assistants, implementing RAG pipelines), enabling developers to get started quickly without building HTTP clients from scratch.","intents":["I want to integrate Perplexity API into my application without building HTTP clients","I need language-native interfaces for API calls (not raw HTTP)","I want to follow best practices and common patterns for using Perplexity API","I need code examples and quickstart guides to get started quickly"],"best_for":["developers building applications in supported SDK languages","teams wanting to follow Perplexity best practices and patterns","builders needing code examples and quickstart guides"],"limitations":["Supported SDK languages not documented (unclear if Python, Node.js, Go, etc. are supported)","SDK maturity and feature completeness not documented","No documented support for async/await or streaming in SDK","No documented support for batch processing or bulk operations","SDK version management and upgrade path not documented"],"requires":["Supported programming language (specific languages unknown)","SDK installation via package manager (pip, npm, etc.)","API key from Perplexity"],"input_types":["text (prompts, queries, configuration)"],"output_types":["structured data (API responses, model outputs)"],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_2","uri":"capability://search.retrieval.raw.web.search.api.with.advanced.filtering.and.ranking","name":"raw web search api with advanced filtering and ranking","description":"The Search API provides direct access to Perplexity's web search infrastructure, returning ranked search results with advanced filtering capabilities. Unlike the Sonar or Agent APIs which generate text responses, the Search API returns raw search results suitable for building custom search UIs, RAG pipelines, or search-augmented applications. Pricing is flat-rate ($5 per 1,000 requests) with no token-based costs, making it cost-predictable for high-volume search workloads.","intents":["I need to build a custom search UI or search results page without generating text responses","I want to feed search results into my own RAG pipeline or knowledge base","I need cost-predictable search infrastructure for high-volume applications","I want to apply custom filtering or ranking logic on top of web search results"],"best_for":["developers building search-first applications (search engines, research tools, discovery platforms)","teams implementing RAG systems that need reliable, ranked search results","builders needing cost-predictable search without token-based pricing"],"limitations":["Returns raw search results only; no text generation or summarization included","Advanced filtering and ranking capabilities mentioned but not detailed in documentation","No documented support for filtering by date range, domain, content type, or other metadata","Result count limits and pagination behavior not specified","No streaming or batch processing support documented"],"requires":["API key from Perplexity","HTTP client for POST requests","Custom logic to process and rank search results (API returns raw results, not processed)"],"input_types":["text (search queries)"],"output_types":["structured data (ranked search results with titles, snippets, URLs, metadata)"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_3","uri":"capability://memory.knowledge.semantic.embeddings.generation.for.rag.and.similarity.search","name":"semantic embeddings generation for rag and similarity search","description":"The Embeddings API generates vector embeddings for text, supporting both standard and contextualized embedding variants. Embeddings can be used for semantic search, similarity matching, and RAG (Retrieval-Augmented Generation) pipelines. The API supports two embedding strategies: standard embeddings for general-purpose similarity, and contextualized embeddings that incorporate surrounding context for improved relevance in domain-specific applications.","intents":["I need to embed documents and queries for semantic search in my RAG system","I want to find similar documents or passages without keyword matching","I need embeddings that understand domain-specific context (e.g., medical, legal, technical documents)","I want to build a vector database for semantic retrieval"],"best_for":["teams building RAG systems with semantic retrieval","developers implementing similarity search or recommendation systems","builders needing domain-aware embeddings for specialized content"],"limitations":["Pricing not documented (documentation page exists but content truncated)","Embedding dimension size not specified","Maximum input length per embedding not documented","Batch processing support not documented","No comparison provided between standard and contextualized embedding quality/cost tradeoffs","No documented support for multi-language embeddings or cross-lingual search"],"requires":["API key from Perplexity","Vector database or similarity search library (e.g., Pinecone, Weaviate, FAISS) to store and query embeddings","Understanding of embedding dimensions and similarity metrics (cosine, dot product, etc.)"],"input_types":["text (documents, passages, queries)"],"output_types":["structured data (vector embeddings as float arrays, embedding metadata)"],"categories":["memory-knowledge","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_4","uri":"capability://tool.use.integration.web.search.tool.invocation.with.autonomous.model.decision.making","name":"web search tool invocation with autonomous model decision-making","description":"Within the Agent API, third-party LLM models can autonomously invoke two web search tools (web_search and fetch_url) via function calling. The model decides when to search based on query content, and Perplexity's infrastructure executes the search and returns results to the model for incorporation into its response. This enables agentic workflows where the model acts as a decision-maker: it can choose to use training data, invoke web_search to retrieve current information, or fetch_url to extract content from specific URLs. Each tool invocation is charged separately ($0.005 for web_search, $0.0005 for fetch_url).","intents":["I want the model to decide whether to search the web or use its training data based on the query","I need to fetch and extract content from specific URLs that the model identifies as relevant","I want to build an agentic system where the model autonomously gathers information before responding","I need fine-grained cost tracking of search tool usage vs model inference"],"best_for":["developers building agentic LLM applications with autonomous search behavior","teams implementing research assistants that need to decide when to search","builders needing transparent cost attribution between inference and tool invocations"],"limitations":["Only two tools available; no custom tool definitions or extensibility","Tool invocation costs are per-call and can accumulate rapidly in multi-step agentic workflows","No documented support for tool result caching or deduplication (repeated searches charged separately)","Model's decision-making for tool invocation is opaque; no control over tool selection strategy","fetch_url behavior not documented (e.g., content extraction method, maximum page size, timeout behavior)","No documented rate limits on tool invocations per request or per time period"],"requires":["API key from Perplexity","Third-party LLM model that supports function calling (OpenAI, Anthropic, Google, xAI)","Understanding of function calling semantics and tool result handling"],"input_types":["text (natural language prompts)","structured function calling schemas for web_search and fetch_url"],"output_types":["text (model response incorporating tool results)","structured tool calls (web_search queries, fetch_url targets)","tool results (search results, fetched page content)"],"categories":["tool-use-integration","search-retrieval","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_5","uri":"capability://search.retrieval.configurable.search.context.depth.for.cost.quality.tradeoffs","name":"configurable search context depth for cost-quality tradeoffs","description":"The Sonar API supports three configurable search context depths (Low, Medium, High) that control how comprehensively the model searches the web during inference. Low context (default) performs minimal search for speed and cost; Medium context balances comprehensiveness and cost; High context performs exhaustive search for research-grade responses. Search context depth directly affects both response latency and pricing, with High context costing 2-3x more than Low context per request. This enables builders to implement dynamic pricing and latency strategies based on query complexity or user tier.","intents":["I want to optimize cost by using shallow search for simple queries and deep search for complex research questions","I need to implement tiered search quality based on user subscription level or query complexity","I want to control the latency-quality tradeoff for different use cases (fast answers vs comprehensive research)","I need to understand how search depth affects both response quality and pricing"],"best_for":["developers building cost-optimized search applications with variable query complexity","teams implementing tiered search quality based on user subscription or query type","builders needing to balance latency and comprehensiveness dynamically"],"limitations":["Only three discrete context depth options (Low/Medium/High); no fine-grained control over search result count or ranking algorithm","No documented guidance on which context depth to use for specific query types or domains","Latency impact of different context depths not specified (no SLAs provided)","Search freshness guarantees not documented (unclear if High context searches more recent sources)","No documented support for per-request context depth configuration in batch operations"],"requires":["API key from Perplexity","Understanding of token-based pricing model (context depth affects request-based pricing, not token pricing)","Application logic to select appropriate context depth based on query or user tier"],"input_types":["text (natural language queries)","context depth parameter (Low, Medium, or High)"],"output_types":["text (model response)","metadata (search context depth used, pricing tier applied)"],"categories":["search-retrieval","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_6","uri":"capability://text.generation.language.citation.generation.and.source.attribution.for.research.responses","name":"citation generation and source attribution for research responses","description":"The Sonar Deep Research model variant includes native citation token generation, automatically extracting and attributing sources from web search results in the model response. Citations are generated as structured tokens (priced at $2/1M tokens) separate from output tokens, enabling builders to extract source attribution without post-processing. This is particularly useful for research applications, fact-checking tools, and content creation where source credibility is critical. Citations include source URLs and context snippets, enabling users to verify claims against original sources.","intents":["I need to generate research responses with automatic source attribution and citations","I want to build a fact-checking tool that shows where claims come from","I need to extract source URLs and context from model responses without manual parsing","I want to provide users with verifiable sources for research content"],"best_for":["teams building research assistants and academic writing tools","developers creating fact-checking or misinformation detection systems","builders implementing content creation tools that require source attribution"],"limitations":["Citation generation only available on Sonar Deep Research variant, not base Sonar or Sonar Pro models","Citation token pricing ($2/1M) is additive to output token pricing, increasing per-response costs","Citation format and structure not documented (unclear if citations are inline, footnotes, or structured metadata)","No documented control over citation density or verbosity (model decides how many citations to generate)","Citation accuracy relative to actual web sources not documented (no SLA for citation correctness)"],"requires":["API key from Perplexity","Use of Sonar Deep Research model variant (not available on base Sonar or Sonar Pro)","Application logic to parse and display citations (format not specified in documentation)"],"input_types":["text (research queries or prompts)"],"output_types":["text (model response with inline citations)","structured data (citation tokens, source URLs, context snippets)"],"categories":["text-generation-language","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_7","uri":"capability://planning.reasoning.reasoning.token.generation.for.multi.step.problem.solving","name":"reasoning token generation for multi-step problem solving","description":"The Sonar Reasoning Pro and Sonar Deep Research models support reasoning tokens, which represent the model's internal reasoning process during inference. Reasoning tokens are generated during problem-solving and are priced separately ($3/1M for Sonar Deep Research, pricing for Sonar Reasoning Pro not documented). This enables builders to observe and optimize the model's reasoning steps, and to implement reasoning-aware pricing where complex problems that require more reasoning steps cost more. Reasoning tokens are particularly useful for research, mathematical problem-solving, and multi-step decision-making tasks.","intents":["I need the model to show its reasoning steps for complex research or problem-solving tasks","I want to understand why the model arrived at a particular conclusion or recommendation","I need to implement pricing that reflects reasoning complexity (more reasoning steps = higher cost)","I want to optimize prompts by observing how many reasoning tokens are generated"],"best_for":["teams building research assistants and decision-support systems","developers implementing educational tools that explain reasoning","builders needing to understand and optimize model reasoning for complex tasks"],"limitations":["Reasoning tokens only available on Sonar Reasoning Pro and Sonar Deep Research variants","Reasoning token pricing ($3/1M for Deep Research) is additive to output token pricing, significantly increasing costs for reasoning-heavy tasks","Reasoning token format and structure not documented (unclear if reasoning is exposed to the API caller or internal only)","No documented control over reasoning depth or verbosity (model decides how much reasoning to generate)","Reasoning token count not predictable from query complexity (no guidance on which queries generate more reasoning tokens)"],"requires":["API key from Perplexity","Use of Sonar Reasoning Pro or Sonar Deep Research model variant","Application logic to parse and display reasoning tokens (format not specified)"],"input_types":["text (complex queries requiring multi-step reasoning)"],"output_types":["text (model response with reasoning steps)","structured data (reasoning tokens, reasoning process metadata)"],"categories":["planning-reasoning","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_8","uri":"capability://tool.use.integration.url.content.extraction.and.processing.via.fetch.url.tool","name":"url content extraction and processing via fetch_url tool","description":"The Agent API includes a fetch_url tool ($0.0005 per invocation) that enables LLM models to retrieve and extract content from specific URLs identified during reasoning or search. When a model invokes fetch_url, Perplexity's infrastructure fetches the page, extracts relevant content (text, structured data, metadata), and returns it to the model for incorporation into the response. This enables agentic workflows where the model can autonomously gather information from specific sources without requiring the application to manage HTTP requests or content extraction.","intents":["I want the model to fetch and analyze content from specific URLs it identifies as relevant","I need to extract structured data or text from web pages without building a web scraper","I want to build an agent that can autonomously gather information from multiple sources","I need to verify claims by fetching and analyzing source documents"],"best_for":["developers building research agents that need to analyze specific sources","teams implementing fact-checking tools that verify claims against source documents","builders creating content analysis or competitive intelligence systems"],"limitations":["fetch_url behavior not documented (content extraction method, maximum page size, timeout behavior, supported content types)","No documented support for authentication (unclear if fetch_url can access paywalled or login-protected content)","No documented support for JavaScript rendering (unclear if fetch_url executes JavaScript or returns raw HTML)","Cost per invocation ($0.0005) can accumulate in multi-step agentic workflows","No documented rate limits or per-request limits on fetch_url invocations","No documented support for batch URL fetching or parallel requests"],"requires":["API key from Perplexity","Third-party LLM model that supports function calling","Valid, publicly accessible URLs (authentication requirements unknown)"],"input_types":["text (URL targets for fetching)"],"output_types":["structured data (extracted page content, metadata, text, structured data)"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__cap_9","uri":"capability://tool.use.integration.transparent.multi.provider.model.pricing.with.no.markup","name":"transparent multi-provider model pricing with no markup","description":"The Agent API implements transparent pricing where third-party LLM models (OpenAI, Anthropic, Google, xAI) are charged at direct provider rates with no Perplexity markup. Model token costs are separated from tool invocation costs (web_search $0.005, fetch_url $0.0005), enabling precise cost attribution. Builders can see exactly how much they're paying for model inference vs tool invocations, and can optimize costs by choosing cheaper models or reducing tool invocations. This contrasts with opaque pricing models where tool costs are bundled into token counts.","intents":["I want to understand exactly what I'm paying for model inference vs tool invocations","I need to optimize costs by comparing different LLM providers without hidden markups","I want to implement cost-aware application logic that chooses models based on price and performance","I need transparent cost attribution for billing and budgeting"],"best_for":["cost-conscious developers building multi-model LLM applications","teams implementing cost optimization strategies across different LLM providers","builders needing transparent cost tracking for billing and budgeting"],"limitations":["Specific per-model pricing not documented in provided content (requires checking Agent API Models page)","Tool invocation costs are additive and can accumulate rapidly in agentic workflows","No documented volume discounts or enterprise pricing","No documented support for cost caps or spending limits","Pricing may change as providers update their rates; no documented notification mechanism for price changes"],"requires":["API key from Perplexity","Understanding of token-based pricing and tool invocation costs","Application logic to track and optimize costs across different models"],"input_types":["text (prompts and queries)"],"output_types":["structured data (cost breakdown: model tokens, tool invocations, total cost)"],"categories":["tool-use-integration","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"perplexity-api__headline","uri":"capability://memory.knowledge.search.augmented.llm.api","name":"search-augmented llm api","description":"The Perplexity API is a search-augmented LLM API that integrates real-time web search capabilities, providing grounded responses with citations, ideal for applications needing up-to-date information.","intents":["best LLM API","LLM API for real-time data","LLM API with web search capabilities","top search-augmented LLM APIs","best API for grounded responses"],"best_for":["applications requiring real-time data","developers needing citation-backed responses"],"limitations":[],"requires":["API key"],"input_types":["text queries"],"output_types":["text responses with citations"],"categories":["memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":58,"verified":false,"data_access_risk":"high","permissions":["API key from Perplexity (created via API Key Management dashboard)","HTTP client capable of POST requests with JSON payloads","Understanding of token-based pricing model (input, output, citation, reasoning tokens charged separately)","API key from Perplexity","No separate API keys for third-party providers required (Perplexity handles provider access)","Understanding of function calling semantics for the chosen LLM provider","Perplexity account with API access enabled","Access to API Key Management dashboard","HTTP client capable of setting Authorization headers","Supported programming language (specific languages unknown)"],"failure_modes":["Search context depth (Low/Medium/High) is coarse-grained; no fine-grained control over search result count or ranking algorithm","Citation generation only available on Sonar Deep Research variant, not base Sonar models","Reasoning tokens (Sonar Reasoning Pro, Deep Research) add significant per-token cost ($3/1M for reasoning output)","No documented SLA for search freshness or latency impact of different context depths","Maximum input/output token limits not specified in documentation","Only two web tools available (web_search and fetch_url); no custom tool definitions or function calling beyond these two","Specific third-party model names/versions not documented; requires checking Agent API Models page for current availability","Tool invocation costs are additive and can accumulate quickly in agentic workflows (web_search at $0.005 per call)","No documented support for streaming or batch processing with Agent API","OpenAI Compatibility mode mentioned but details not provided; unclear which OpenAI features are supported","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7,"quality":0.9,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:25.060Z","last_scraped_at":null,"last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=perplexity-api","compare_url":"https://unfragile.ai/compare?artifact=perplexity-api"}},"signature":"c4ckhtvbu/+Ya1qBSRVKv+iRI6cU71VlshhNEvqlyf/AfU5+fg93OTb16HyDhLYFHYs7bo7rVydRDzCJYBeXBA==","signedAt":"2026-06-21T20:37:31.891Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/perplexity-api","artifact":"https://unfragile.ai/perplexity-api","verify":"https://unfragile.ai/api/v1/verify?slug=perplexity-api","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}