Perplexity AI
AI-powered search and research assistant. Requesty routes to 3 Perplexity AI models starting at $1.00 per 1M input tokens with context windows up to 205K tokens. One API key, OpenAI-compatible SDK, no markup.
All Perplexity AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
sonar-reasoning-pro | 131K | 8K | $2.00 | $8.00 | — | |
sonar | 131K | 8K | $1.00 | $1.00 | — | |
sonar-pro | 205K | 8K | $3.00 | $15.00 | — |
About Perplexity AI on Requesty
How many Perplexity AI models are available through Requesty?
Requesty routes to 3 Perplexity AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Perplexity AI model?
The cheapest Perplexity AI model starts at $1.00 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Perplexity AI pricing?
No. Requesty passes through exactly what Perplexity AI charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Perplexity AI models?
Perplexity AI's training policy varies by product and tier. See their privacy policy for specifics, and contact Requesty for enterprise-grade data controls.
Where are Perplexity AI models hosted?
Perplexity AI models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Perplexity AI rows in the models explorer.