Perplexity API
Web search, agent, embeddings and decision APIs from Perplexity, billed per request or per token
Perplexity API is Perplexity's developer platform. The Search API returns raw web results at $5 per 1,000 requests, or $1 with Fast Search. The Agent API runs third-party models from OpenAI, Anthropic, Google, xAI, Z.AI, Moonshot AI and NVIDIA at their published token rates, with web search, URL fetch and a code sandbox as paid tools.
It also serves pplx-embed embedding models from $0.004 per 1M tokens and a Decisions API for the open pplx-decider-v1-27b decision model. Billing is prepaid credits. Perplexity documents zero retention of prompt data by default and holds a SOC 2 Type II report.
Pricing: Usage-based
Perplexity API Alternatives
Explore 119 products in the Inference APIs category. View all Perplexity API alternatives.
Miapi
Web-grounded AI answers API with citations, OpenAI-compatible, pay-per-query pricing
CheapestInference
Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows
Perplexity pplx-decider
Perplexity's open decision model: typed yes/no, choice and score answers with probabilities, by API or open weights
Work on Perplexity API? Feature it at the top of Inference APIs.
Is your product missing?