Perplexity
PerplexitySonar Pro
Perplexity's Sonar Pro search-grounded model for deeper answers with citations; priced via Perplexity's Sonar API hosts (OpenRouter and peers).
Active
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).
Source: Perplexity API pricing, Perplexity docs
Price per 1M tokens via OpenRouter
$3 in / $15 out
Context window200,000
Max output8,192
ModalitiesText, Image → Text
Specs
Details that do not fit the rate card above.
Billing noteToken rates plus per-request search context fees on Perplexity's Sonar API
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate |
|---|---|
| Input | $3 / M |
| Output | $15 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Provider
Where this model runs, and what it charges.
| Platform | Input / M | Output / M | Batch | Access |
|---|---|---|---|---|
Perplexity | from$3 | $15 | — | via OpenRouter |
Price history
Has this model gotten cheaper or more expensive?
No changePriced at $3 / $15 per 1M since August 7, 2026.
More from Perplexity
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Sonar Pro call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.