aid: parallel-ai name: Parallel description: >- Parallel Web Systems builds web APIs purpose-built for AI agents: a high-accuracy Search API, an Extract API that turns URLs into clean LLM-ready markdown, a Task/Deep Research API with tiered processors (lite through ultra), FindAll for natural-language entity discovery and enrichment, a Monitor API for scheduled web-change tracking, an OpenAI-compatible Responses and Chat Completions pair, and a Memory API that lets agents reuse past research. The platform is API-key authenticated over https://api.parallel.ai, ships official Python and TypeScript SDKs and a CLI, emits Standard Webhooks and SSE event streams, and is SOC 2 Type I/II certified. Its agent surface is unusually complete: an anonymous hosted MCP server whose tools are publicly introspectable, an OAuth-gated Task MCP server, a conformant A2A agent card backed by a live /a2a endpoint, provider-published Agent Skills with a discovery document, an llms.txt, and markdown twins of every documentation page. Pricing is pay-as-you-go per request per product. Originally surfaced as a Kleiner Perkins portfolio company and enriched from Parallel's public developer surface. url: https://raw.githubusercontent.com/api-evangelist/parallel-ai/refs/heads/main/apis.yml deliveryModel: model: saas open_source: false commercial: true callable_host: true label: Hosted service ยท you call their endpoint confidence: high source: - openapi - pricing generated: '2026-08-28' method: derived accessModel: pricing: pay-as-you-go onboarding: self-serve trial: true try_now: true public: true label: Self-serve signup, pay-as-you-go, free tier confidence: high notes: >- Published per-request rate card (plans/parallel-plans-pricing.yml); up to $80 signup credit and $5/month free credits; hosted playgrounds per product; and an MCP endpoint at https://search.parallel.ai/mcp callable with no account and no API key at all. source: - https://docs.parallel.ai/getting-started/pricing - https://parallel.ai/pricing - https://docs.parallel.ai/integrations/mcp/search-mcp generated: '2026-08-14' method: searched image: https://cdn.sanity.io/images/5hzduz3y/production/3e8afb3fd62096a800a8135910fdc375971e17ba-3600x1890.jpg?w=1200&h=630&fit=crop x-type: company x-source: kleiner-perkins-portfolio specificationVersion: '0.23' created: '2026-07-17' modified: '2026-08-14' x-docs-platform: mintlify x-docs-platform-confidence: medium x-docs-platform-checked: 2026-10-17 x-docs-hosting: vercel tags: - Company - Artificial Intelligence - Web Search - Agents - Deep Research - Web Extraction - Data Enrichment - Web Monitoring - LLM Tools - A2A - AI Agents - MCP - Agent Skills - Content Extraction - Entity Resolution tags_raw: - Company - Ai - Web Search - Agents - Deep Research - Web Extraction - Data Enrichment - Web Monitoring - LLM Tools - A2A - Ai Ml - AI Agents - MCP - Agent Skills - Content Extraction - Entity Resolution apis: - aid: parallel-ai:parallel-ai-chat-api-beta-api name: Parallel Chat API (Beta) API description: >- The Chat API provides a programmatic chat-style text generation interface. It accepts a sequence of messages and returns model responses. Intended for assistant-like interactions and evaluation. Streaming responses are supported. humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Chat API (Beta) properties: - type: OpenAPI url: openapi/parallel-ai-chat-api-beta-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-extract-api name: Parallel Extract API description: >- Extract returns excerpts or full content from one or more URLs. Inputs are a list of URLs and an optional search objective and keyword queries. The returned excerpts or full content is formatted as markdown and suitable for LLM consumption. - Result: excerpts or full content from the URL formatted as markdown humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Extract properties: - type: OpenAPI url: openapi/parallel-ai-extract-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-findall-api name: Parallel Find All API description: >- The FindAll API discovers and evaluates entities that match complex criteria from natural language objectives. Submit a high-level goal and the service automatically generates structured match conditions, discovers relevant candidates, and evaluates each against the criteria. Returns comprehensive results with detailed reasoning, citations, and confidence scores for each match decision. Streaming events and webhooks are supported. humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - FindAll properties: - type: OpenAPI url: openapi/parallel-ai-findall-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-memory-api name: Parallel Memory API description: >- The Memory API retrieves and manages memories created by Tasks, Monitors, and FindAll runs. Memories can be personal or isolated with a `memory_scope_key`. humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Memory properties: - type: OpenAPI url: openapi/parallel-ai-memory-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-monitor-api name: Parallel Monitor API description: >- The Monitor API watches the web for material changes on a fixed frequency. Each monitor runs once on creation and then on its configured schedule, emitting events when meaningful changes are detected. - `event_stream` monitors track a search query and emit an event for each new material change. - `snapshot` monitors track a specific task run's output and emit an event when the output changes. Results can be polled via the events endpoint or delivered via webhooks. humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Monitors tags_raw: - Monitor properties: - type: OpenAPI url: openapi/parallel-ai-monitor-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-responses-api-api name: Parallel Responses API description: >- An OpenAI-Responses-compatible interface for answers grounded in live web research, with URL citations. Point any Responses-API client โ€” the OpenAI Python SDK, OpenAI TypeScript SDK, the Agents SDK, or raw HTTP โ€” at `https://api.parallel.ai` with your Parallel API key, set `model` to `parallel`, and call `/v1/responses`. - `input` accepts a plain string or an array of role/content messages (canonical OpenAI shape; text content only). - `reasoning.effort` (`low`/`medium`/`high`) controls how much research is performed, trading response time for answer quality. - Multi-turn via `previous_response_id`. - Structured outputs via `text.format = {"type": "json_schema", "name": ..., "schema": {...}}`. - Streaming (`stream=true`) emits the standard OpenAI Responses SSE lifecycle: `response.created` and `response.in_progress`, then output item / content part / text delta events with URL-citation annotations, the matching `*.done` events, and a terminal `response.completed` โ€” or `response.failed` if the request fails mid-stream. humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Responses API properties: - type: OpenAPI url: openapi/parallel-ai-responses-api-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-search-api name: Parallel Search API description: >- Search returns ranked URLs with extended excerpts suitable for LLM consumption. Inputs are a natural-language objective and optional keyword queries. Source policies allow including or excluding specific domains and have configurable output sizes. The returned extended snippets contain dense, relevant information from relevant pages. - Result: ranked list with URL, title, and long text excerpts humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Search properties: - type: OpenAPI url: openapi/parallel-ai-search-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart - aid: parallel-ai:parallel-ai-tasks-api name: Parallel Tasks API description: >- The Task API executes web research and extraction tasks. Clients submit a natural-language objective with an optional input schema; the service plans retrieval, fetches relevant URLs, and returns outputs that conform to a provided or inferred JSON schema. Supports deep research style queries and can return rich structured JSON outputs. Processors trade-off between cost, latency, and quality. Each processor supports calibrated confidences. - Output metadata: citations, excerpts, reasoning, and confidence per field Task Groups enable batch execution of many independent Task runs with group-level monitoring and failure handling. - Submit hundreds or thousands of Tasks as a single group - Observe group progress and receive results as they complete - Real-time updates via Server-Sent Events (SSE) - Add tasks to an existing group while it is running - Group-level retry and error aggregation humanURL: https://docs.parallel.ai/getting-started/overview baseURL: https://api.parallel.ai tags: - Task tags_raw: - Tasks properties: - type: OpenAPI url: openapi/parallel-ai-tasks-api-openapi.yml - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Authentication url: authentication/parallel-authentication.yml - type: Documentation url: https://docs.parallel.ai/resources/memory - type: Documentation url: https://docs.parallel.ai/responses-api/responses-quickstart maintainers: - FN: Kin Lane email: kin@apievangelist.com - FN: APIs.json email: info@apis.io common: - type: CapabilityMap url: capabilities/parallel-ai-capability-edges.yml name: Parallel Business Capability Map - type: PostmanWorkspace url: https://www.postman.com/kinlaneapi/parallel/overview - type: Website url: https://www.parallel.ai - type: DeveloperPortal url: https://platform.parallel.ai - type: Documentation url: https://docs.parallel.ai/home - type: APIReference url: https://docs.parallel.ai/api-reference - type: GettingStarted url: https://docs.parallel.ai/getting-started/overview - type: Pricing url: https://docs.parallel.ai/getting-started/pricing - type: Blog url: https://parallel.ai/blog - type: GitHubOrganization url: https://github.com/parallel-web - type: SignUp url: https://platform.parallel.ai - type: Support url: https://docs.parallel.ai/resources/faqs - type: TermsOfService url: https://parallel.ai/terms-of-service - type: PrivacyPolicy url: https://parallel.ai/privacy-policy - type: ChangeLog url: changelog/parallel-changelog.yml - type: StatusPage url: https://status.parallel.ai/ - type: Deprecation url: lifecycle/parallel-lifecycle.yml - type: Authentication url: authentication/parallel-authentication.yml - type: Packages url: packages/parallel-packages.yml - type: SDKs url: packages/parallel-packages.yml - type: CLI url: cli/parallel-cli.yml - type: MCPServer url: mcp/parallel-mcp.yml - type: AgentSkill url: skills/_index.yml - type: LLMsTxt url: llms/parallel-llms.txt - type: Overlay url: overlays/parallel-openapi-overlay.yaml - type: WellKnown url: well-known/parallel-well-known.yml - type: Conformance url: conformance/parallel-conformance.yml - type: Compliance url: security/parallel-trust-center.yml - type: TrustCenter url: security/parallel-trust-center.yml - type: ErrorCatalog url: errors/parallel-problem-types.yml - type: Lifecycle url: lifecycle/parallel-lifecycle.yml - type: Conventions url: conventions/parallel-conventions.yml - type: DataModel url: data-model/parallel-data-model.yml - type: RateLimits url: rate-limits/parallel-rate-limits.yml - type: Webhooks url: asyncapi/parallel-webhooks.yml - type: DomainSecurity url: security/parallel-domain-security.yml - type: AgenticAccess url: agentic-access/parallel-agentic-access.yml - type: AgentCard url: a2a/parallel-a2a.yml - type: ToolCrosswalk url: mcp/parallel-tool-crosswalk.yml - type: Plans url: plans/parallel-plans-pricing.yml - type: OAuthScopes url: scopes/parallel-scopes.yml - type: Sandbox url: sandbox/parallel-sandbox.yml - type: Postman url: https://www.postman.com/kinlaneapi/parallel/overview - type: Contact url: mailto:partnerships@parallel.ai - type: Website url: https://parallel.ai/ - type: Documentation url: https://docs.parallel.ai - type: APIReference url: https://docs.parallel.ai/api-reference/search/search x-enrichment: date: '2026-08-14' status: enriched artifacts_added: 12 pass: local-v1 x-a2a: verified: true probed: '2026-09-26' url: "https://api.parallel.ai/.well-known/agent-card.json" grade: "conformant" protocol_version: "0.3.0" control: 404