Independent technical audit

docs.parallel.ai

Overall AI readiness score

A combined result across all audit signals.

Average

AI readiness audit: 8/16/2026Public technical data

Overall AI readiness assessment

How ready docs.parallel.ai is for AI systems

74/100

Parallel (docs.parallel.ai) received an AI-readiness score of 74/100 in an automated technical audit. llms.txt was accessible, llms-full.txt was accessible, and ai.txt was not found. The robots.txt analysis found 0 explicitly allowed and 0 blocked AI crawlers, with 1 declared sitemap. Homepage markup completeness was 0%; no Schema.org types were detected and 0 OpenGraph tags were detected. Results reflect the public site response observed on 2026-08-16T00:26:27.778Z.

Audit context

llms.txt is accessible and contains 5,175 tokens. An expanded llms-full.txt is also available with 245,157 tokens, giving agents more direct context. No separate ai.txt policy was detected; it is optional, but can clarify training, retrieval, and attribution preferences.

robots.txt is available. 11 of 11 tracked AI bots are not blocked. Declared sitemaps: 1. No Schema.org type was detected on the homepage. 0 OpenGraph tags were found and markup completeness is 0%, leaving more entity interpretation to crawlers.

The mobile Lighthouse profile adds Performance 49/100, Accessibility 93/100, Best Practices 100/100, SEO 100/100, and experimental Agentic Browsing 100/100. These signals have a limited weight: they complement rather than replace llms.txt, robots.txt, and structured-data checks.

Confirmed strengths

Accessible llms.txt
Expanded llms-full.txt
1 sitemap declaration
Strong Google agentic signals

Priority improvements

1Add JSON-LD for the organisation, website, and core entities.
2Complete OpenGraph and canonical homepage metadata.
3Reduce mobile rendering delay and main-thread work.

llms.txt tokens5,175

llms-full.txt tokens245,157

ai.txt

sitemap.xml

Google Lighthouse technical profile

A mobile Lighthouse measurement. Google’s experimental Agentic Browsing category is explained separately and does not replace the broader llmsmap AI-readiness score.

Mobile · Lighthouse

Performance

Accessibility

100

Best Practices

100

Technical SEO

100

Agentic Browsing

What these results mean

Mobile performance is 49/100, with the largest visible content block appearing in 11.8 s and the browser main thread blocked for 480 ms. Layout shift was 0. The main thread is where the browser runs JavaScript, calculates layout, and paints the page; long work there delays both user input and browser-agent actions.

Accessibility scored 93/100, Best Practices 100/100, and technical SEO 100/100. The experimental Agentic Browsing category scored 100/100. It measures signals Google currently tests for software agents and is shown separately from the llmsmap AI-readiness score.

Free the main thread and accelerate the first view

Split long JavaScript tasks, defer non-critical scripts and styles, and shorten blocking request chains. This helps the primary content appear sooner and makes controls usable earlier.

Reduce code that loads without helping the page

Remove unused CSS and JavaScript, load heavy widgets on demand, and limit third-party scripts. Less code means less parsing and background work on the device.

Optimise images and their loading order

Serve correctly sized modern formats, prioritise the primary visual, and lazy-load content below the first viewport.

Reduce network delay

Improve server response time, remove unnecessary redirects and repeat downloads, and use compression, caching, and selective preconnect hints.

FCP4.7 s

First content

LCP11.8 s

Main content

CLS0

Layout stability

TBT480 ms

Blocking time

SI6.3 s

Visual speed

Metric glossary

FCP · First content: When the first text or image appeared on screen.
LCP · Main content: When the largest visible element in the first viewport rendered.
CLS · Layout stability: How much content shifted unexpectedly while loading; lower is better.
TBT · Blocking time: How long the browser main thread could not respond quickly to input.
SI · Visual speed: How quickly the visible viewport filled with content.

8/16/2026Lighthouse 13.4.1Mobile profile

AI readiness checks

Machine-readable files, crawler policy, discovery, and homepage markup.

llms.txt

File found and accessible

https://docs.parallel.ai/llms.txt

llms-full.txt

Full version is available

https://docs.parallel.ai/llms-full.txt

ai.txt

ai.txt file was not found

robots.txt

File found

https://docs.parallel.ai/robots.txt

Sitemap in robots.txt1

1 sitemap found

Schema.org (JSON-LD)

Schema.org markup was not found on the homepage

OpenGraph

OpenGraph tags were not found on the homepage

AI bot access

Based on robots.txt analysis

GPTBotNot mentioned

OAI-SearchBotNot mentioned

ChatGPT-UserNot mentioned

Google-ExtendedNot mentioned

ClaudeBotNot mentioned

Claude-SearchBotNot mentioned

Claude-UserNot mentioned

BytespiderNot mentioned

CCBotNot mentioned

PerplexityBotNot mentioned

Perplexity-UserNot mentioned

Sitemaps

Declared discovery routes for crawlers and agents.

https://docs.parallel.ai/sitemap.xml

# Parallel

> Parallel's web APIs (Search, Extract, Task/Deep Research, FindAll, Chat, and Monitor) give AI agents and developers high-quality, low-latency access to the web for research, content extraction, entity discovery, and continuous monitoring.

## Docs

- [Parallel API Overview](https://docs.parallel.ai/getting-started/overview.md): Explore Parallel's web API products for building intelligent applications.
- [Parallel API Pricing](https://docs.parallel.ai/getting-started/pricing.md)
- [API Rate Limits](https://docs.parallel.ai/getting-started/rate-limits.md): Default API rate limits for Search, Extract, Tasks, Chat, FindAll, and Monitor endpoints
- [Parallel API Glossary](https://docs.parallel.ai/getting-started/glossary.md): Key terms and concepts used throughout Parallel's documentation
- [Search API Quickstart](https://docs.parallel.ai/search/search-quickstart.md): Execute natural language web searches and retrieve LLM-optimized excerpts with the Parallel Search API
- [Search API Best Practices](https://docs.parallel.ai/search/best-practices.md): Craft effective objectives and search queries for the Parallel Search API, including tool-calling agents and evals
- [Search Modes](https://docs.parallel.ai/search/modes.md): Configure the Search API mode for your use case
- [Migrate to Parallel Search](https://docs.parallel.ai/search/migrate-to-parallel.md): Move from Exa, Tavily, SERP APIs, or built-in model search to the Parallel Search API
- [Advanced Search Settings](https://docs.parallel.ai/search/advanced-search-settings.md): Advanced configuration for source policy, fetch policy, excerpt settings, location, and result count
- [Source Policy](https://docs.parallel.ai/search/source-policy.md)
- [Search MCP](https://docs.parallel.ai/search/search-mcp.md)
- [Upgrade from Beta to GA](https://docs.parallel.ai/search/search-migration-guide.md): Migrate from Beta to GA (V1) Search API
- [Extract API Quickstart](https://docs.parallel.ai/extract/extract-quickstart.md): Convert any public URL into clean, LLM-optimized markdown with the Parallel Extract API
- [Extract API Best Practices](https://docs.parallel.ai/extract/best-practices.md): Learn how to optimize web content extraction with objectives, search queries, and fetch policies for LLM-ready markdown output
- [Advanced Extract Settings](https://docs.parallel.ai/extract/advanced-extract-settings.md): Advanced configuration for fetch policy, excerpt settings, and full content extraction
- [Extract Migration Guide: Beta to GA](https://docs.parallel.ai/extract/extract-migration-guide.md): Migrate from Beta to GA (V1) Extract API
- [Task API Quickstart](https://docs.parallel.ai/task-api/task-quickstart.md): Transform complex knowledge work into programmable, repeatable operations powered by AI web research
- [Task API Best Practices](https://docs.parallel.ai/task-api/best-practices.md): Best practices for writing Task Specs and caching outputs when using Parallel's agent products
- [Task Spec](https://docs.parallel.ai/task-api/guides/specify-a-task.md): Define structured research tasks with customizable input and output schemas.
- [Processors](https://docs.parallel.ai/task-api/guides/choose-a-processor.md): Select the right Task API processor (lite, base, core, pro, ultra) based on task complexity and latency requirements
- [Task Runs Lifecycle](https://docs.parallel.ai/task-api/guides/execute-task-run.md): Understanding how Tasks Runs are created, processed, and returned
- [Research Basis](https://docs.parallel.ai/task-api/guides/access-research-basis.md): Understand how to access citations, reasoning, and confidence levels for your Task Run outputs
- [Interactions](https://docs.parallel.ai/task-api/guides/interactions.md): Chain context across multiple API calls using interaction IDs
- [Interactive Research](https://docs.parallel.ai/task-api/examples/interactive-research.md): Build an interactive research app with multi-turn context chaining
- [Task API Deep Research Quickstart](https://docs.parallel.ai/task-api/examples/task-deep-research.md): Transform natural language queries into comprehensive intelligence reports
- [Task API Enrichment Quickstart](https://docs.parallel.ai/task-api/examples/task-enrichment.md): Enrich your structured data with web intelligence using the Task API
- [Task API Webhooks](https://docs.parallel.ai/task-api/webhooks.md): Webhook events for task run completions
- [Task Group](https://docs.parallel.ai/task-api/group-api.md): Batch process Tasks at scale with the Parallel Task Group API
- [Ingest API](https://docs.parallel.ai/task-api/ingest-api.md): API reference for creating awesome tasks
- [Task API Streaming Events](https://docs.parallel.ai/task-api/task-sse.md): SSE for Task Runs
- [MCP Tool Calling](https://docs.parallel.ai/task-api/mcp-tool-call.md): Using MCP servers for tool calls in Tasks
- [Task MCP](https://docs.parallel.ai/task-api/task-mcp.md)
- [Source Policy](https://docs.parallel.ai/task-api/source-policy.md)
- [OpenAI ChatCompletions Compatibility](https://docs.parallel.ai/chat-api/chat-quickstart.md): Build low-latency web research applications with OpenAI-compatible streaming chat completions
- [Responses API Quickstart](https://docs.parallel.ai/responses-api/responses-quickstart.md): Answer questions with live web research in seconds
- [Statefulness](https://docs.parallel.ai/responses-api/features/statefulness.md): Multi-turn conversations with the Responses API using `previous_response_id`
- [Responses API Structured Outputs](https://docs.parallel.ai/responses-api/features/structured-outputs.md): Get JSON answers conforming to your schema from the Responses API
- [Responses API Streaming Events](https://docs.parallel.ai/responses-api/features/streaming-events.md): Stream Responses API results as server-sent events
- [Citations](https://docs.parallel.ai/responses-api/features/citations.md): Source annotations on Responses API answers
- [Using the Responses API Directly](https://docs.parallel.ai/responses-api/examples/direct-requests.md): Call the Responses API directly: single questions, deep research, dataset enrichment, and follow-ups
- [Using It as a Research Subagent](https://docs.parallel.ai/responses-api/examples/research-subagent.md): Expose the Responses API as a web-research tool that another LLM can call
- [OpenAI Responses Compatibility](https://docs.parallel.ai/responses-api/openai-compatibility.md): Field-by-field compatibility reference for the OpenAI Responses wire format
- [FindAll API Quickstart](https://docs.parallel.ai/findall-api/findall-quickstart.md): Discover and enrich entities from the web using natural language queries with the FindAll API
- [Entity Search](https://docs.parallel.ai/findall-api/entity-search.md): Fast, synchronous people and company search, the real-time counterpart to FindAll — describe what you need in natural language and receive a set of matching results in seconds
- [Generators](https://docs.parallel.ai/findall-api/core-concepts/findall-generator-pricing.md): Choose the right FindAll generator (preview, base, core, pro) based on query complexity and expected match volume
- [Candidates](https://docs.parallel.ai/findall-api/core-concepts/findall-candidates.md): Understanding FindAll candidates, their structure, states, and how to exclude specific entities
- [Run Lifecycle](https://docs.parallel.ai/findall-api/core-concepts/findall-lifecycle.md): Understand FindAll run statuses, termination reasons, and how to cancel runs
- [Preview](https://docs.parallel.ai/findall-api/features/findall-preview.md): Test FindAll queries with a small sample of candidates before committing to full runs
- [Enrichments](https://docs.parallel.ai/findall-api/features/findall-enrich.md): Add non-boolean enrichment data to FindAll candidates without affecting match conditions
- [FindAll API Streaming Events](https://docs.parallel.ai/findall-api/features/findall-sse.md): Receive real-time updates on FindAll runs using Server-Sent Events (SSE)
- [FindAll API Webhooks](https://docs.parallel.ai/findall-api/features/findall-webhook.md): Receive real-time notifications on FindAll runs and candidates using webhooks
- [Extend](https://docs.parallel.ai/findall-api/features/findall-extend.md): Increase the match limit of existing FindAll runs to get more results without changing query criteria
- [Cancel](https://docs.parallel.ai/findall-api/features/findall-cancel.md): Stop FindAll runs early to control costs
- [Refresh Runs](https://docs.parallel.ai/findall-api/features/findall-refresh.md): Rerun the same FindAll query with exclude_list to discover net new entities over time
- [Monitor API Quickstart](https://docs.parallel.ai/monitor-api/monitor-quickstart.md): Continuously track web changes with scheduled queries and webhook notifications using the Monitor API
- [Events](https://docs.parallel.ai/monitor-api/monitor-events.md): Understand monitor event types and how to retrieve them
- [Monitor API Webhooks](https://docs.parallel.ai/monitor-api/monitor-webhooks.md): Receive real-time notifications for Monitor executions and detected events using webhooks
- [Slack Integration](https://docs.parallel.ai/monitor-api/monitor-slack.md): Set up Monitor in Slack to receive real-time web updates directly in your channels
- [Create a Snapshot Monitor](https://docs.parallel.ai/monitor-api/quickstart-snapshot.md): Monitor any task output for material changes on a schedule
- [Follow-up Tasks](https://docs.parallel.ai/monitor-api/monitor-task.md): Trigger Task API enrichment or deep research from a monitor event
- [Monitor Migration Guide: Alpha to GA](https://docs.parallel.ai/monitor-api/monitor-migration-guide.md): Migrate from the Alpha Monitor API (/v1alpha) to the GA version (/v1)
- [Developer Tools Overview](https://docs.parallel.ai/integrations/developer-quickstart.md): Choose the right way to integrate Parallel into your AI workflow — CLI, MCP, or SDK
- [Account API](https://docs.parallel.ai/integrations/account-api.md): Authenticate with the Parallel Account API using device-based OAuth 2.0
- [Install Parallel Agent Skills with npx skills](https://docs.parallel.ai/integrations/agent-skills.md): Use npx skills add to give Cursor, Cline, GitHub Copilot, Windsurf, and 30+ AI coding agents Parallel web search, extraction, deep research, and data enrichment.
- [Anthropic Tool Calling](https://docs.parallel.ai/integrations/anthropic-tool-calling.md): Use Parallel Search as a tool with Anthropic's Claude models for real-time web access
- [Claude Code Plugin](https://docs.parallel.ai/integrations/claude-code-marketplace.md): Add Parallel web search, extraction, deep research, and data enrichment to Claude Code
- [OpenClaw Skills for Web Search and Research](https://docs.parallel.ai/integrations/clawhub.md): What OpenClaw skills are, how to install them from ClawHub, and how to give OpenClaw web search, content extraction, deep research, and data enrichment with Parallel.
- [Parallel CLI](https://docs.parallel.ai/integrations/cli.md): Command-line tool for web search, content extraction, data enrichment, deep research, entity discovery, and web monitoring
- [Cursor Plugin](https://docs.parallel.ai/integrations/cursor-marketplace.md): Add Parallel web search, extraction, deep research, and data enrichment to Cursor
- [LangChain](https://docs.parallel.ai/integrations/langchain.md): LangChain integrations for Parallel, enabling real-time web research and AI capabilities
- [Parallel MCP Server Quickstart](https://docs.parallel.ai/integrations/mcp/quickstart.md): Install and configure Parallel MCP servers for AI assistants like Cursor, VS Code, and Claude Desktop
- [Programmatic Use](https://docs.parallel.ai/integrations/mcp/programmatic-use.md): How to use the MCP servers Programmatically
- [Search MCP](https://docs.parallel.ai/integrations/mcp/search-mcp.md): Add real-time web search and content extraction to AI agents with the Parallel Search MCP Server
- [Task MCP](https://docs.parallel.ai/integrations/mcp/task-mcp.md): Enable deep research and data enrichment workflows in AI assistants with the Parallel Task MCP Server
- [OAuth Provider](https://docs.parallel.ai/integrations/oauth-provider.md): Integrate with the Parallel OAuth Provider to get a Parallel API key on behalf of your users
- [Ollama Tool Calling](https://docs.parallel.ai/integrations/ollama-tool-calling.md): Use Parallel Search as a tool with local Ollama models for real-time web access
- [OpenAI Tool Calling](https://docs.parallel.ai/integrations/openai-tool-calling.md): Use Parallel Search as a tool with OpenAI's function calling to give GPT models real-time web access
- [OpenCode Plugin](https://docs.parallel.ai/integrations/opencode-plugin.md): Add Parallel web search and content extraction to OpenCode
- [Pi Extension](https://docs.parallel.ai/integrations/pi-extension.md): Add Parallel web search and content extraction to Pi
- [Agentic Payments (MPP & x402)](https://docs.parallel.ai/integrations/agentic-payments.md): Enable AI agents to make autonomous payments using Parallel and the Machine Payments Protocol via Stripe or Tempo stablecoins
- [AWS Marketplace](https://docs.parallel.ai/integrations/aws-marketplace.md): Access Parallel's API through the AWS Marketplace
- [Browser Use](https://docs.parallel.ai/integrations/browseruse.md): Access private web data in Tasks using Browser Use MCP
- [Google Cloud Marketplace](https://docs.parallel.ai/integrations/google-cloud-marketplace.md): Subscribe to Parallel via Google Cloud Marketplace
- [Google Gemini Enterprise](https://docs.parallel.ai/integrations/google-gemini-enterprise.md): Use Parallel as a grounding provider in Google Gemini Enterprise Agent Platform
- [Google Sheets](https://docs.parallel.ai/integrations/gsuite.md): Use Parallel directly in Google Sheets with the PARALLEL_QUERY function
- [n8n](https://docs.parallel.ai/integrations/n8n.md): Use Parallel in n8n Automations
- [OpenRouter](https://docs.parallel.ai/integrations/openrouter.md): Use Parallel as a web search engine on OpenRouter
- [Superhuman](https://docs.parallel.ai/integrations/superhuman.md): Use Parallel with Superhuman
- [Vercel](https://docs.parallel.ai/integrations/vercel.md): Use Parallel with Vercel
- [Zapier](https://docs.parallel.ai/integrations/zapier.md): Use Parallel in Zapier workflows
- [Data Integrations](https://docs.parallel.ai/data-integrations/overview.md): Enrich your data with web intelligence directly in your favorite data tools
- [Apache Spark](https://docs.parallel.ai/data-integrations/spark.md): Enrich data at scale using Parallel's SQL-native UDFs for Apache Spark
- [DuckDB](https://docs.parallel.ai/data-integrations/duckdb.md): Enrich data at scale using Parallel's native DuckDB integration with batch processing
- [Google BigQuery](https://docs.parallel.ai/data-integrations/bigquery.md): Enrich data at scale using Parallel's SQL-native remote functions for BigQuery
- [Polars](https://docs.parallel.ai/data-integrations/polars.md): Enrich data at scale using Parallel's native Polars integration for DataFrames
- [Snowflake](https://docs.parallel.ai/data-integrations/snowflake.md): Enrich data at scale using Parallel's SQL-native UDTF for Snowflake
- [Supabase](https://docs.parallel.ai/data-integrations/supabase.md): Enrich your Supabase data with live web intelligence using Edge Functions and Parallel
- [Use Parallel Memory to Build on Past Research](https://docs.parallel.ai/resources/memory.md): Let your agents search and reuse past Task, Monitor, and FindAll results so new research builds on work you have already done.
- [Organization roles and permissions](https://docs.parallel.ai/resources/organization-roles-and-permissions.md): See the permissions available to Members and Admins in your Parallel organization.
- [Source Policy](https://docs.parallel.ai/resources/source-policy.md): Control which sources are used in web research, including domain allow/deny lists and a freshness start date.
- [API Error Codes and Warnings](https://docs.parallel.ai/resources/warnings-and-errors.md): Breakdown of warnings and errors
- [Webhook Setup](https://docs.parallel.ai/resources/webhook-setup.md): Guide to configuring and verifying webhooks for Parallel APIs
- [FindAll Migration Guide](https://docs.parallel.ai/findall-api/findall-migration-guide.md): Guide for migrating from V0 to V1 FindAll API
- [Crawler](https://docs.parallel.ai/resources/crawler.md): This documentation provides guidance for webmasters on managing their website's interaction with our crawling system
- [Status Page](https://docs.parallel.ai/resources/status.md)
- [Parallel API FAQs](https://docs.parallel.ai/resources/faqs.md): Frequently asked questions about Parallel APIs, billing, security, and platform features
- [Search](https://docs.parallel.ai/api-reference/search/search.md): Searches the web.
- [Extract](https://docs.parallel.ai/api-reference/extract/extract.md): Extracts relevant content from specific web URLs.
- [Create Task Group](https://docs.parallel.ai/api-reference/tasks/create-task-group.md): Initiates a TaskGroup to group and track multiple runs.
- [Retrieve Task Group](https://docs.parallel.ai/api-reference/tasks/retrieve-task-group.md): Retrieves aggregated status across runs in a TaskGroup.
- [Stream Task Group Events](https://docs.parallel.ai/api-reference/tasks/stream-task-group-events.md): Streams events from a TaskGroup: status updates and run completions.
- [Fetch Task Group Runs](https://docs.parallel.ai/api-reference/tasks/fetch-task-group-runs.md): Retrieves task runs in a TaskGroup and optionally their inputs and outputs.
- [Add Runs to Task Group](https://docs.parallel.ai/api-reference/tasks/add-runs-to-task-group.md): Initiates multiple task runs within a TaskGroup.
- [Retrieve Task Group Run](https://docs.parallel.ai/api-reference/tasks/retrieve-task-group-run.md): Retrieves run status by run_id.
- [Create Task Run](https://docs.parallel.ai/api-reference/tasks/create-task-run.md): Initiates a task run.
- [Retrieve Task Run](https://docs.parallel.ai/api-reference/tasks/retrieve-task-run.md): Retrieves run status by run_id.
- [Stream Task Run Events](https://docs.parallel.ai/api-reference/tasks/stream-task-run-events.md): Streams events for a task run.
- [Retrieve Task Run Input](https://docs.parallel.ai/api-reference/tasks/retrieve-task-run-input.md): Retrieves the input of a run by run_id.
- [Retrieve Task Run Result](https://docs.parallel.ai/api-reference/tasks/retrieve-task-run-result.md): Retrieves a run result by run_id, blocking until the run is completed.
- [Stream Task Run Events](https://docs.parallel.ai/api-reference/tasks/stream-task-run-events-1.md): Streams events for a task run.
- [Fast Entity Search](https://docs.parallel.ai/api-reference/findall/fast-entity-search.md): Return ranked entities matching a natural language objective.
- [Ingest FindAll Run](https://docs.parallel.ai/api-reference/findall/ingest-findall-run.md): Transforms a natural language search objective into a structured FindAll spec.
- [Create FindAll Run](https://docs.parallel.ai/api-reference/findall/create-findall-run.md): Starts a FindAll run.
- [Retrieve FindAll Run Status](https://docs.parallel.ai/api-reference/findall/retrieve-findall-run-status.md): Retrieve a FindAll run.
- [Cancel FindAll Run](https://docs.parallel.ai/api-reference/findall/cancel-findall-run.md): Cancel a FindAll run.
- [Add Enrichment to FindAll Run](https://docs.parallel.ai/api-reference/findall/add-enrichment-to-findall-run.md): Add an enrichment to a FindAll run.
- [Stream FindAll Events](https://docs.parallel.ai/api-reference/findall/stream-findall-events.md): Stream events from a FindAll run.
- [Extend FindAll Run](https://docs.parallel.ai/api-reference/findall/extend-findall-run.md): Extend a FindAll run by adding additional matches to the current match limit.
- [FindAll Run Result](https://docs.parallel.ai/api-reference/findall/findall-run-result.md): Retrieve the FindAll run result at the time of the request.
- [Get FindAll Run Schema](https://docs.parallel.ai/api-reference/findall/get-findall-run-schema.md)
- [List Monitors](https://docs.parallel.ai/api-reference/monitor/list-monitors.md): List monitors ordered by creation time, newest first.
- [Create Monitor](https://docs.parallel.ai/api-reference/monitor/create-monitor.md): Create a monitor.
- [Retrieve Monitor](https://docs.parallel.ai/api-reference/monitor/retrieve-monitor.md): Retrieve a monitor.
- [Cancel Monitor](https://docs.parallel.ai/api-reference/monitor/cancel-monitor.md): Cancel a monitor.
- [List Monitor Events](https://docs.parallel.ai/api-reference/monitor/list-monitor-events.md): List events for a monitor, newest first.
- [Trigger Monitor Run](https://docs.parallel.ai/api-reference/monitor/trigger-monitor-run.md): Trigger an immediate monitor run.
- [Update Monitor](https://docs.parallel.ai/api-reference/monitor/update-monitor.md): Update a monitor.
- [Clear Memory](https://docs.parallel.ai/api-reference/memory/clear-memory.md): Clears all entries from the selected memory without deleting the underlying tasks, monitors, or FindAll runs.
- [Evict from Memory](https://docs.parallel.ai/api-reference/memory/evict-from-memory.md): Removes a task run, monitor, or FindAll run from the selected memory without deleting the original resource.
- [Retrieve Memory](https://docs.parallel.ai/api-reference/memory/retrieve-memory.md): Retrieves relevant or recent runs from the selected memory. Provide a query to rank results by relevance; leave it empty to return the most recent runs.
- [Chat Completions](https://docs.parallel.ai/api-reference/chat-api-beta/chat-completions.md): Chat completions.
- [Create Response](https://docs.parallel.ai/api-reference/responses-api/create-response.md): Create a response.
- [Get Balance](https://docs.parallel.ai/service-api/balance/get-balance.md): Get the authenticated organization's prepaid credit balance
- [Add to Balance](https://docs.parallel.ai/service-api/balance/add-to-balance.md): Charge the organization's default payment method and add the amount to the prepaid credit balance. The default payment method configured on the org's Stripe customer is always used; no payment method id is accepted from the client.
- [List Apps](https://docs.parallel.ai/service-api/apps/list-apps.md): List all apps for the authenticated organization
- [Create App](https://docs.parallel.ai/service-api/apps/create-app.md): Create a new app for the authenticated organization
- [Delete App](https://docs.parallel.ai/service-api/apps/delete-app.md): Delete an app from the authenticated organization
- [Create Key](https://docs.parallel.ai/service-api/keys/create-key.md): Create a new API key for an app
- [Delete Key](https://docs.parallel.ai/service-api/keys/delete-key.md): Delete an API key from an app
- [Parallel API Changelog](https://docs.parallel.ai/resources/changelog.md): Product updates from the Parallel team

## OpenAPI Specs

- [openapi](https://api.parallel.ai/account/service/openapi.json)
- [public-openapi](https://docs.parallel.ai/public-openapi.json)
- [docs-latest-openapi](https://docs.parallel.ai/docs-latest-openapi.json)
- [docs-legacy-openapi](https://docs.parallel.ai/docs-legacy-openapi.json)

## Optional

- [Get API Key](https://platform.parallel.ai)
- [OpenAPI Spec](https://docs.parallel.ai/public-openapi.json)
- [Python SDK](https://pypi.org/project/parallel-web/)
- [TypeScript SDK](https://www.npmjs.com/package/parallel-web)

Share or continue the analysis

Share this audit

Discuss with AI

Added 8/16/2026