Perplexity Sonar API

"Power your products with unparalleled real-time, web-wide research and Q&A capabilities." [1]

docs.perplexity.ai · By Perplexity · Agent JSON · Suggest an edit · Last verified 2026-06-14 · Source confidence: high

Perplexity Sonar API is a REST-based search and language model service that lets developers add real-time web retrieval, Q&A with inline citations, deep research, and semantic embeddings to their products. Pricing is usage-based starting at $1.00 per million tokens, with self-serve signup and no sales call required. The API ships SDKs for Python, TypeScript, and Node.js MCP, holds SOC 2 Type 2 certification, enforces a zero data-retention policy, and counts Samsung among its documented customers.

Best for / Avoid if

Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box

Avoid if: You want to try it free before paying

Scores

  • 90 / 100
    Agent friendliness
  • 85 / 100
    Pricing transparency
  • 60 / 100
    Setup speed
  • 90 / 100
    Docs quality
  • 85 / 100
    Procurement ease
  • 25 / 100
    Trust readiness

Scores are computed deterministically from this profile's published, sourced fields (pricing, compliance, capabilities, docs and developer-surface signals) - not from reviews or paid placement. Each axis is 0-100; an unknown signal scores 0 for that axis. Procurement ease is the inverse of buying friction (higher = easier to adopt).

Pricing & procurement

Pricing model
Usage-based
Published pricing
Yes
Free tier
No
Self-serve signup
Yes
Requires sales call
No
Enterprise plan
Yes [2]
Published prices
PlanItemPerAmountSource
Sonarinput tokens1M tokens$1source
Sonaroutput tokens1M tokens$1source
Sonarrequest fee (low search context)1,000 requests$5source
Sonarrequest fee (medium search context)1,000 requests$8source
Sonarrequest fee (high search context)1,000 requests$12source
Sonar Proinput tokens1M tokens$3source
Sonar Prooutput tokens1M tokens$15source
Sonar Prorequest fee (low search context)1,000 requests$6source
Sonar Prorequest fee (medium search context)1,000 requests$10source
Sonar Prorequest fee (high search context)1,000 requests$14source
Sonar ProPro Search request fee (fast/standard, low context)1,000 requests$6source
Sonar ProPro Search request fee (fast/standard, medium context)1,000 requests$10source
Sonar ProPro Search request fee (fast/standard, high context)1,000 requests$14source
Sonar ProPro Search request fee (pro/multi-step, low context)1,000 requests$14source
Sonar ProPro Search request fee (pro/multi-step, medium context)1,000 requests$18source
Sonar ProPro Search request fee (pro/multi-step, high context)1,000 requests$22source
Sonar Reasoning Proinput tokens1M tokens$2source
Sonar Reasoning Prooutput tokens1M tokens$8source
Sonar Reasoning Prorequest fee (low search context)1,000 requests$6source
Sonar Reasoning Prorequest fee (medium search context)1,000 requests$10source
Sonar Reasoning Prorequest fee (high search context)1,000 requests$14source
Sonar Deep Researchinput tokens1M tokens$2source
Sonar Deep Researchoutput tokens1M tokens$8source
Sonar Deep Researchcitation tokens1M tokens$2source
Sonar Deep Researchreasoning tokens1M tokens$3source
Sonar Deep Researchsearch queries1,000 queries$5source
Search APIweb search requests1,000 requests$5source
Embeddings APIpplx-embed-v1-0.6b tokens1M tokens$0.004source
Embeddings APIpplx-embed-v1-4b tokens1M tokens$0.03source
Embeddings APIpplx-embed-context-v1-0.6b (contextualized) tokens1M tokens$0.008source
Embeddings APIpplx-embed-context-v1-4b (contextualized) tokens1M tokens$0.05source
Agent APIweb_search tool callcall$0.005source
Agent APIfetch_url tool callcall$0.0005source
Agent APIpeople_search tool callcall$0.005source
Agent APIfinance_search tool callcall$0.005source
Agent APIsandbox session (20-minute window)session$0.03source

Capabilities

  • AI answer
  • Semantic / neural
  • Agent-ready / MCP
  • Zero data retention
Supported actions
chat_completions_with_web_search (POST /v1/chat/completions), async_chat_completions (POST /v1/async/sonar), get_async_response (GET /v1/async/sonar/{api_request}), list_async_requests (GET /v1/async/sonar), web_search (POST /v1/search), embeddings (POST /v1/embeddings), contextualized_embeddings (POST /v1/embeddings/contextualized), agent_completions (POST /v1/agent), list_models (GET /v1/models)
Regions
Global web index; compute hosted on AWS in North America [3]
Languages
Queries accepted in multiple languages via ISO 639-1 search_language_filter parameter (up to 10 languages per request); English is primary
Input types
natural language query, structured chat messages (OpenAI-compatible), domain filter arrays, date/recency filters, ISO 639-1 language filter, ISO 3166 country/location filter, base64-encoded images, HTTPS image URLs
Output types
JSON (OpenAI-compatible chat completion), streaming server-sent events, citations array with source URLs, search_results metadata, token usage metrics, structured JSON schema output, vector embeddings
Webhooks
No
Sandbox / test mode
No
SDK languages
Python, TypeScript, MCP (Node.js) [4]
MCP server
Yes [5]

Trust & compliance

SOC 2
SOC 2 Type II [6]
HIPAA
No [7]
GDPR
Unknown
ISO 27001
Unknown
PCI DSS
Unknown
Published SLA
No [8]
Rate limits
Tier-based RPM by model. Sonar / Sonar Pro / Sonar Reasoning Pro: Tier 0=50 RPM, Tier 1=150, Tier 2=500, Tier 3=1,000, Tier 4=4,000, Tier 5=4,000. Sonar Deep Research: Tier 0=5, Tier 1=10, Tier 2=20, Tier 3=40, Tier 4=60, Tier 5=100 RPM. Search API: 50 req/s fixed across all tiers. Tiers advance by cumulative lifetime spend: Tier 1=$50+, Tier 2=$250+, Tier 3=$500+, Tier 4=$1,000+, Tier 5=$5,000+. [9]
Known restrictions
Zero data retention policy: no customer prompt/response data is retained after request processing, Customer data is never used for model training, Protected Health Information cannot be processed without a signed Business Associate Agreement, Fine-tuning of models is not supported, No uptime SLA or service quality guarantees published ('We do not guarantee this at the moment'), SafeSearch content filtering is on by default, Domain and date filters cannot be combined in certain ways; max 20 domains per filter, Perplexity may suspend access for applications deemed competitive with Perplexity, Search API Terms of Service explicitly states no enhanced security obligations or uptime guarantees apply to Search Services

Developer surface

Docs rendering: static · markdown variants served · llms.txt present

Integration

API style
rest
Base URL
https://api.perplexity.ai
Version
v1
Versioning
url
Stability
ga
Auth methods
api_key
Idempotency keys
No
Error format
vendor-specific
Rate limit
50 / minute

SDKs

  • Python perplexityai · repo
  • TypeScript @perplexity-ai/perplexity_ai · repo
  • MCP (Node.js) @perplexity-ai/mcp-server · repo

Adoption & maturity

Launched
2023-10-04
GA
2025-01-01
Notable customers
Samsung

Other Web Search APIs

  • Firecrawl

    The API to search, scrape, and interact with the web at scale.

    Subscription · free tier · public pricing · self-serve

  • Exa

    "Web search, built for AI agents. One API for search, crawling, and research agents."

    Usage · free tier · public pricing · self-serve

  • Brave Search API

    "The Brave Search API provides developers with access to Brave Search results and enables building AI products, chatbots, coding assistants, and AI-search engines with real-time web data."

    Usage · public pricing · self-serve

  • Tavily Search API

    "Real-time search, extraction, research, and web crawling through a single, secure API."

    Hybrid · free tier · public pricing · self-serve

  • Linkup

    "Production-grade Web Search API for AI"

    Usage · free tier · public pricing · self-serve

  • Jina AI Search Foundation (DeepSearch / Reader)

    "Your Search Foundation, Supercharged."

    Usage · public pricing · self-serve

Perplexity Sonar API alternatives · Perplexity Sonar API vs Firecrawl · All Web Search APIs APIs

References

Each field above carries a numbered source - hover for a preview, click to jump here.

  1. Description: docs.perplexity.ai
  2. Enterprise plan: perplexity.ai
  3. Regions: docs.perplexity.ai
  4. SDK languages: docs.perplexity.ai
  5. MCP server: github.com · docs.perplexity.ai
  6. SOC 2: docs.perplexity.ai
  7. HIPAA: docs.perplexity.ai · hub-prod.perplexity.ai
  8. Published SLA: docs.perplexity.ai · perplexity.ai
  9. Rate limits: docs.perplexity.ai · docs.perplexity.ai

Change history

Every field change, who made it, and when - from our audited data pipeline and editors.

  1. 2026-06-15 Score Agent Friendliness: 6090
  2. 2026-06-15 Score Docs Quality: 5590
  3. 2026-06-14 Robots Allows Agents: (none)Yes
  4. 2026-06-14 Markdown Docs URL: (none)https://docs.perplexity.ai/docs.md
  5. 2026-06-14 Has Structured Data: (none)Yes
  6. 2026-06-14 API Reference URL: (none)https://docs.perplexity.ai/api-reference/agent-post
  7. 2026-06-14 Markdown Docs Served: (none)Yes
  8. 2026-06-14 Capabilities: {}{"semantic":true,"ai_answer":true,"agent_ready":true,"zero_retention":true}
  9. 2026-06-14 Summary Md: (none)Perplexity Sonar API is a REST-based search and language model service that let…
  10. 2026-06-14 Best For: (none)Regulated or enterprise workloads - compliance attestations and an enterprise p…
  11. 2026-06-14 Score Agent Friendliness: (none)60
  12. 2026-06-14 Score Pricing Transparency: (none)85
  13. 2026-06-14 Score Setup Speed: (none)60
  14. 2026-06-14 Score Docs Quality: (none)55
  15. 2026-06-14 Score Procurement Friction: (none)85
  16. 2026-06-14 Score Trust Readiness: (none)25
  17. 2026-06-14 Avoid If: (none)You want to try it free before paying
  18. 2026-06-14 Scoring Methodology: (none)Scores are computed deterministically from this profile's published, sourced fi…
  19. 2026-06-14 Llms Txt Present: (none)Yes
  20. 2026-06-14 Docs URL: (none)https://docs.perplexity.ai/docs
  21. 2026-06-14 Changelog URL: (none)https://docs.perplexity.ai/changelog
  22. 2026-06-14 Openapi Spec URL: (none)https://docs.perplexity.ai/openapi.json
  23. 2026-06-14 Rendering: (none)static
  24. 2026-06-14 Llms Txt URL: (none)https://docs.perplexity.ai/llms.txt
  25. 2026-06-14 SLA Published: set to No
  26. 2026-06-14 Data Retention Policy URL: set to https://docs.perplexity.ai/docs/resources/privacy-security
  27. 2026-06-14 Documented Rate Limits: set to Tier-based RPM by model. Sonar / Sonar Pro / Sonar Reasoning Pro: Tier 0=50 RPM…
  28. 2026-06-14 Rate Limit Requests: set to 50
  29. 2026-06-14 Rate Limit Window: set to minute
  30. 2026-06-14 Known Restrictions: set to Zero data retention policy: no customer prompt/response data is retained after …
  31. 2026-06-14 Auth Methods: set to api_key
  32. 2026-06-14 Auth Docs URL: set to https://docs.perplexity.ai/docs/getting-started/quickstart
  33. 2026-06-14 API Style: set to rest
  34. 2026-06-14 Base URL: set to https://api.perplexity.ai
  35. 2026-06-14 API Version: set to v1
  36. 2026-06-14 Versioning Scheme: set to url
  37. 2026-06-14 Stability: set to ga
  38. 2026-06-14 Deprecation Policy URL: set to https://docs.perplexity.ai/changelog/changelog
  39. 2026-06-14 MCP URL: set to https://docs.perplexity.ai/guides/mcp-server
  40. 2026-06-14 Quickstart URL: set to https://docs.perplexity.ai/docs/getting-started/quickstart
  41. 2026-06-14 Idempotency Supported: set to No
  42. 2026-06-14 Error Format: set to vendor-specific
  43. 2026-06-14 Requires Verification: set to No
  44. 2026-06-14 Starting Price Usd: set to 1
  45. 2026-06-14 Price Basis: set to 1M tokens
  46. 2026-06-14 Launched At: set to 2023-10-04
  47. 2026-06-14 GA Date: set to 2025-01-01
  48. 2026-06-14 Slug: set to perplexity-sonar
  49. 2026-06-14 Fields Not Found: set to iso_27001, gdpr, pci_dss, free_tier_details, minimum_commitment, context_window…
  50. 2026-06-14 Source Confidence: set to high

Suggest an edit / leave a review

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

Leave a review or comment

curl -X POST https://apio.sh/api/feedback/perplexity-sonar \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

Suggest a correction to a field (cite a source)

curl -X POST https://apio.sh/api/suggest/perplexity-sonar/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →