Perplexity

Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.

Use when you want grounded answers without building search+cite yourself. For full agent stacks, prefer Exa/Tavily + your LLM.

Pricing notes

As of 2026-09-14 (docs.perplexity.ai pricing): Sonar $1/$1 per 1M in/out; Sonar Pro $3/$15; Sonar Reasoning Pro $2/$8; Sonar Deep Research $2/$8 + citation $2/1M + search queries $5/1K + reasoning $3/1M. Request fees per 1K (low/med/high context): Sonar $5/$8/$12; Sonar Pro & Reasoning Pro $6/$10/$14. Pro Search (Sonar Pro) $14/$18/$22. Search API $5/1K requests. Agent tools: web_search $0.0025, fetch_url $0.0005, people/finance_search $0.005, sandbox $0.03/session. Embeddings pplx-embed-v1-0.6b $0.004/1M; 4b $0.03/1M. Consumer Pro ≠ API billing. Note: Sonar Chat Completions→Agent API migration; Sonar supported until 2026-09-27.

Sourced pricing

Contract status ambiguous · multiple_sourced_token_skus. Single normalized $/1M: null. Machine list: /api/pricing?provider=perplexity

• pplx-embed-v1-0.6b · usd_per_million_tokens · $0.004 · sourced_token_price
• pplx-embed-v1-4b · usd_per_million_tokens · $0.03 · sourced_token_price
• pplx-embed-context-v1-0.6b · usd_per_million_tokens · $0.008 · sourced_token_price
• pplx-embed-context-v1-4b · usd_per_million_tokens · $0.05 · sourced_token_price
• web search tool search_type=web · usd_per_1k_calls · $2.5 · unit_mismatch · normalized null