Skip to content
ModelCap

Inference provider

Perplexity: AI models and API pricing

Every tracked model Perplexity serves through OpenRouter, with Perplexity's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 11 August 2026

Perplexity serves 5 tracked models through 5 endpoints as of 11 August 2026; the highest-ranked is Sonar Deep Research (ModelCap Index #151); mean measured uptime is 100.0%.

Models served
5
On the ModelCap Index
5
Cheapest output price
$1.00/1M

Language models on Perplexity (5)

Ranked models first, in ModelCap Index order. Prices are the lowest Perplexity lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Perplexity, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Sonar Deep ResearchPerplexity#15125.5$2.00$8.00128K——1
2Sonar Pro SearchPerplexity#15225.5$3.00$15.00200K—100.0%1
3SonarPerplexity#15325.5$1.00$1.00127K—100.0%1
4Sonar Reasoning ProPerplexity#17725.3$2.00$8.00128K——1
5Sonar ProPerplexity#2212.6$3.00$15.00200K—100.0%1

Perplexity on ModelCap: common questions

How many AI models does Perplexity serve?

5 tracked models as of 11 August 2026: 5 language models (5 with a public ModelCap Index position), across 5 live endpoints observed through OpenRouter.

What is the best model available on Perplexity?

Sonar Deep Research from Perplexity is the highest-ranked language model Perplexity serves, at ModelCap Index position #151 and $8.00 per 1M output tokens on Perplexity. The table lists every model in Index order.

What is the cheapest model on Perplexity?

Sonar at $1.00 per 1M output tokens ($1.00 per 1M input), the lowest positive language-token price Perplexity lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Perplexity model has the largest context window?

Sonar Pro Search, served with a 200K-token context window on Perplexity. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Perplexity?

Mean measured uptime across Perplexity endpoints is 100.0% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Perplexity prices come from?

From the OpenRouter catalogue entry for each Perplexity endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Perplexity exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further