Rank #2 of 5 in AI Search APIs
vs Exa
vs Tavily
vs Brave Search API
vs SerpApiShowcase
Products
Perplexity, product by product →Perplexity ships more than one product — each judged line competes in its own arena on the same stories as everyone else.
| Line | Arena | Rank | PA Score | Agent-ready |
|---|---|---|---|---|
| Perplexity | AI Assistants | #4/9 | 25/100 | 49/100 |
| Sonar APIthis page | AI Search APIs | #2/5 | 33/100 | 56/100 |
Not yet judged (1 — no arena where they compete): Comet
Verified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Citations trust — stories about citations trust in this arenaCitations trustevidence →
Stories about citations trust in this arena
Content extraction — stories about content extraction in this arenaContent extractionevidence →
Stories about content extraction in this arena
Filters controls — stories about filters controls in this arenaFilters controlsevidence →
Stories about filters controls in this arena
Freshness coverage — stories about freshness coverage in this arenaFreshness coverageevidence →
Stories about freshness coverage in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Search quality — stories about search quality in this arenaSearch qualityevidence →
Stories about search quality in this arena
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 0 free · 10 paid · 0 enterprise · 15 not stated in evidence
Follow the green: where the map greys out is where Perplexity Sonar API stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
✓9/10
unlocks → Webhooks · Scoped API keys · Versioning policy · API sandbox
Subscribe to events via webhooks
—–
Build against official SDKs
✓8/10
Issue scoped/least-privilege API credentials for an agent
—–
Connect an agent via an official MCP server
✓8/10
Download a machine-readable API spec (OpenAPI or equivalent)
✓9/10
Rely on versioned APIs with a documented deprecation policy
—–
Test against a sandbox environment without touching production data
—–
Explore an interactive API reference with runnable examples
~6/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓9/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~6/10
unlocks → MCP client
Operate the product with natural-language commands
✓7/10
unlocks → Autonomous automations
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
~5/10
Set up automations that run autonomously in the background
—–
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Citations trust — stories about citations trust in this arenaCitations trust
Stories about citations trust in this arena
Content extraction — stories about content extraction in this arenaContent extraction
Stories about content extraction in this arena
Filters controls — stories about filters controls in this arenaFilters controls
Stories about filters controls in this arena
Freshness coverage — stories about freshness coverage in this arenaFreshness coverage
Stories about freshness coverage in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Search quality — stories about search quality in this arenaSearch quality
Stories about search quality in this arena
Sorted by importance (agentic first) (high → low) · 50/50 stories · click a row’s chevron for the rationale and evidence
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 9/10 | Tprobed | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Tprobed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partialpaid | 6/10 | Cclaimed | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Cclaimed | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Cclaimed | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Cclaimed | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | none | untested | none yet | |
Get results sized and ranked for direct use as LLM context in a RAG pipeline C Llm ready results | developer | Search quality — stories about search quality in this arenaSearch quality | 3 | fullpaid | 8/10 | Cclaimed | |
Plug the API into an agent as a ready-made tool, with function-calling schemas and agent-framework integrations designed for direct tool-call consumption C Ai consumption | ai-native user | Search quality — stories about search quality in this arenaSearch quality | 3 | full | 8/10 | Tprobed | |
Run meaning-based semantic search that finds results keyword engines miss C Retrieval modes | developer | Search quality — stories about search quality in this arenaSearch quality | 3 | partial | 6/10 | Cclaimed | |
See clear per-request or per-credit pricing without talking to sales G Pricing clarity | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 3 | partial | 6/10 | Cclaimed | |
Get fresh results with date-range and recency filters backed by a frequently updated index C Freshness | data engineer | Freshness coverage — stories about freshness coverage in this arenaFreshness coverage | 3 | partialpaid | 4/10 | Cclaimed | |
Rely on results carrying canonical URLs, titles, and published dates so my app can cite sources accurately C Citation fidelity | developer | Citations trust — stories about citations trust in this arenaCitations trust | 3 | partialpaid | 4/10 | Cclaimed | |
Retrieve full page text or markdown for results, not just snippets C Page contents | developer | Content extraction — stories about content extraction in this arenaContent extraction | 3 | partialpaid | 4/10 | Cclaimed | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | n/a | untested | none yet | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Get a sourced, LLM-generated answer to a query in a single API call C Llm ready results | developer | Search quality — stories about search quality in this arenaSearch quality | 2 | fullpaid | 9/10 | Cclaimed | |
Get structured output matching a JSON schema I define C Page contents | developer | Content extraction — stories about content extraction in this arenaContent extraction | 2 | full | 8/10 | Cclaimed | |
Have an agent run a multi-step research flow — search, extract contents, and synthesize — through one API C Ai consumption | ai-native user | Content extraction — stories about content extraction in this arenaContent extraction | 2 | fullpaid | 8/10 | Cclaimed | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 6/10 | Cclaimed | |
Read documented rate limits and concurrency caps with a self-serve upgrade path G Pricing clarity | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | partial | 6/10 | Cclaimed | |
Restrict or exclude specific domains from my search results C Query filters | developer | Filters controls — stories about filters controls in this arenaFilters controls | 2 | partialpaid | 5/10 | Cclaimed | |
Query dedicated verticals like news, images, or finance through specific endpoints or category filters C Freshness | data engineer | Freshness coverage — stories about freshness coverage in this arenaFreshness coverage | 2 | partial | 4/10 | Cclaimed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partialpaid | 3/10 | Cclaimed | |
Prototype against the API on a free tier or free credits G Pricing clarity | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | nonepaid | 0/10 | ||
Choose between keyword, neural, or hybrid retrieval modes per query C Retrieval modes | developer | Search quality — stories about search quality in this arenaSearch quality | 2 | none | untested | none yet | |
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Localize results by country, language, or location parameters C Targeting | data engineer | Freshness coverage — stories about freshness coverage in this arenaFreshness coverage | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Read a documented stance on robots.txt, content licensing, and permitted use of results C Citation fidelity | data engineer | Citations trust — stories about citations trust in this arenaCitations trust | 2 | none | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
Submit batched or asynchronous jobs for high-volume query workloads C Scale throughput | data engineer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | none | untested | none yet | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 3/10 | Cclaimed | |
Crawl subpages or entire sites starting from a search result C Page contents | data engineer | Content extraction — stories about content extraction in this arenaContent extraction | 1 | none | 0/10 | ||
Read per-result relevance scores to threshold what enters my pipeline C Query filters | developer | Filters controls — stories about filters controls in this arenaFilters controls | 1 | none | 0/10 | ||
Find pages similar to a URL I already have C Retrieval modes | developer | Search quality — stories about search quality in this arenaSearch quality | 1 | none | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 35 stories with headroom
What would move Perplexity Sonar API’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
The evidence only shows Perplexity publishing its own MCP server (and an Anthropic-side MCP connector for consuming Perplexity's tools) — i.e., Perplexity acts as the tool provider, not as a client that ingests third-party MCP servers' tools.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
Missing: any self-hosted deployment option, open-source core engine/model weights, or on-prem offering.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
No evidence in the pack addresses data usage for training, opt-out settings, or a privacy/data-retention policy for API data; nothing in the docs pack mentions training-data opt-out at all.
Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the background
nonemoves Built-in AIimpact 30
The evidence describes building agents via the Agent API (tools, sandbox, model fallback, profiles, multi-turn context) but nothing about scheduling, triggers, or autonomous background execution without a caller invoking the API — it's a request/response API, not a background-automation runtime.
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent
nonemoves agent-readyimpact 30
The evidence covers API key generation, rate-limit tiers, and tool-restriction for MCP servers, but there is no mention of scoped or least-privilege API credentials (e.g., per-key permissions, role-based scopes, restricted key creation for sub-agents).
Agenticness — how well agents can access and operate the productSubscribe to events via webhooks
nonemoves agent-readyimpact 30
No evidence of any webhook/event subscription mechanism in the Sonar API docs; the product offers request/response APIs, SDKs, CLI, and MCP integration but nothing about outbound event notifications or webhooks.
Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy
nonemoves API qualityimpact 30
The evidence pack shows extensive API documentation, SDKs, an OpenAPI spec, and product features, but nowhere mentions API versioning scheme, a deprecation policy, model sunset timelines, or changelog practices.
Automation depth — how much of the product can run unattendedSchedule recurring jobs or workflows
nonemoves PA Scoreimpact 20
No evidence in the pack mentions any scheduling, cron, recurring job, or workflow automation trigger feature for Sonar/Agent API; the docs cover search, agents, tools, MCP, routing, and SDKs but nothing about persisting or scheduling recurring runs.
Showing the top 8 of 35 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map5 surfaces · 27 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
docs27 stories
- Point an agent at llms.txt or agent-oriented docs
- Run the product headlessly / in CI for automation
- Connect an agent via an official MCP server
- Use an official CLI
- Drive the product through a documented public API
- Build against official SDKs
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Explore an interactive API reference with runnable examples
- Download a machine-readable API spec (OpenAPI or equivalent)
- Perform bulk operations across many items at once
- Version, review, and roll back my automations
- Rely on results carrying canonical URLs, titles, and published dates so my app can cite sources accurately
- Have an agent run a multi-step research flow — search, extract contents, and synthesize — through one API
- Retrieve full page text or markdown for results, not just snippets
- Get structured output matching a JSON schema I define
- Restrict or exclude specific domains from my search results
- Get fresh results with date-range and recency filters backed by a frequently updated index
- Query dedicated verticals like news, images, or finance through specific endpoints or category filters
- Do everything through the API that I can do in the UI
- Read documented rate limits and concurrency caps with a self-serve upgrade path
- See clear per-request or per-credit pricing without talking to sales
- Plug the API into an agent as a ready-made tool, with function-calling schemas and agent-framework integrations designed for direct tool-call consumption
- Get a sourced, LLM-generated answer to a query in a single API call
- Get results sized and ranked for direct use as LLM context in a RAG pipeline
- Run meaning-based semantic search that finds results keyword engines miss
OpenAPI spec6 stories
- Point an agent at llms.txt or agent-oriented docs
- Run the product headlessly / in CI for automation
- Drive the product through a documented public API
- Explore an interactive API reference with runnable examples
- Download a machine-readable API spec (OpenAPI or equivalent)
- Plug the API into an agent as a ready-made tool, with function-calling schemas and agent-framework integrations designed for direct tool-call consumption
API reference5 stories
- Drive the product through a documented public API
- Explore an interactive API reference with runnable examples
- Rely on results carrying canonical URLs, titles, and published dates so my app can cite sources accurately
- Get a sourced, LLM-generated answer to a query in a single API call
- Get results sized and ranked for direct use as LLM context in a RAG pipeline
GitHub README4 stories
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
4 of 15 testable claims verified · 2 contradicted → integrity 0/100
24 distinct capability claims found in Perplexity Sonar API’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
4
Verified
9
Unverified
2
Contradicted
14
Undersold
Verified (6)
“Official MCP Server lets AI assistants use Perplexity's search and reasoning in their workflows”
“Can restrict which tools the model may call by disabling tools by default and enabling only specific ones”
Plug the API into an agent as a ready-made tool, with function-calling schemas and agent-framework integrations designed for direct tool-call consumptionfullproof ↗
“Unified OpenAI-compatible endpoint provides access to open-weight models hosted by Perplexity”
Drive the product through a documented public APIfullproof ↗
“Interactive Playground lets users try Perplexity Search without an API key”
Explore an interactive API reference with runnable examplespartialproof ↗
“Remote hosted MCP server available at a fixed URL requiring no installation or updates”
“Tools can be used with the Agent API for tool-calling workflows”
Plug the API into an agent as a ready-made tool, with function-calling schemas and agent-framework integrations designed for direct tool-call consumptionfullproof ↗
Unverified (10)
“Get web-grounded answers with built-in citations in a single API call”
Get a sourced, LLM-generated answer to a query in a single API callfullproof ↗
“Get raw, ranked web search results with advanced filtering and real-time data”
Get fresh results with date-range and recency filters backed by a frequently updated indexpartialproof ↗
“Generate embeddings for semantic search and RAG pipelines”
Run meaning-based semantic search that finds results keyword engines misspartialproof ↗
“Pro Search mode adds automated multi-step tool use, running multiple web searches and fetching URLs to answer complex queries”
Have an agent run a multi-step research flow — search, extract contents, and synthesize — through one APIfullproof ↗
“Official SDKs provide type-safe integration”
“Official CLI runs Perplexity Search from the terminal, returning JSON for shell pipelines and agent tool calls with no code required”
“API usage automatically advances accounts to higher rate-limit tiers as spend increases, with permanent tier retention”
Read documented rate limits and concurrency caps with a self-serve upgrade pathpartialproof ↗
“Search API supports ranked results, domain filtering, multi-query search, and content extraction”
Restrict or exclude specific domains from my search resultspartialproof ↗
“SDKs include type definitions for all request params and response fields, with sync and async clients”
“Responses include citations and search_results fields for source attribution”
Rely on results carrying canonical URLs, titles, and published dates so my app can cite sources accuratelypartialproof ↗
Contradicted (2)
“Local open-source MCP server can be run on your own machine over stdio”
“Perplexity's tools can be used in a Messages API request via an MCP connector”
Plug MCP servers into this product so it can use their toolsnoneproof ↗
Undersold (14)
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Run the product headlessly / in CI for automationfullproof ↗
Get AI-generated insights and suggestions from my data inside the productpartialproof ↗
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
Operate the product with natural-language commandsfullproof ↗
Download a machine-readable API spec (OpenAPI or equivalent)fullproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Retrieve full page text or markdown for results, not just snippetspartialproof ↗
Get structured output matching a JSON schema I definefullproof ↗
Query dedicated verticals like news, images, or finance through specific endpoints or category filterspartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
See clear per-request or per-credit pricing without talking to salespartialproof ↗
Get results sized and ranked for direct use as LLM context in a RAG pipelinefullproof ↗
Claims outside our story set (6)
Real capability claims found in Perplexity Sonar API’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Access third-party models from OpenAI, Anthropic, Google, and xAI with web search tools and presets”
source ↗“Search context size setting controls how much web information is retrieved per query”
source ↗“Supports streaming responses via Server Side Events (SSE)”
source ↗“Certain errors are automatically retried with exponential backoff”
source ↗“Errors raise typed exceptions (subclasses of APIStatusError) with status_code and response properties”
source ↗“Async client can use aiohttp as an alternative HTTP backend for improved concurrency”
source ↗
Pricing signals
- $5per 1k searchespay-as-you-goSearch API: charged per successful POST /search request (up to 5 queries per request = one billing unit)source ↗as of 2026-09-07
- $5per 1k searchespay-as-you-goSonar model, low search-context request fee (also has token pricing separately)source ↗as of 2026-09-07
- $6per 1k searchespay-as-you-goSonar Pro model, low search-context request fee (fast search type)source ↗as of 2026-09-07
- $14per 1k searchespay-as-you-goSonar Pro with Pro Search (multi-step tool usage), low context request feesource ↗as of 2026-09-07
Extracted verbatim from the vendor’s own pricing page — hover a figure for the exact quote.
Business model
Prepaid-credit, usage-based API pricing per 1k requests plus per-token model fees across Sonar tiers; higher rate-limit usage tiers unlock with cumulative spend.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
Agent surface uptime llms.txt 100% · openapi.json 100% (30d, checked every 6h since Sep 8 '26)