← All models

Anthropic

sonar-reasoning-pro

perplexity/sonar-reasoning-pro

Price per million tokens

Input
$2.532
Output
$10.128
Cache write
not offered
Cache read
not offered

What you pay. It is what the tokens cost us to buy plus 20%, and your usage page shows what we paid beside what you paid on every request you send.

Limits

Context window
128,000 tokens
Max output
provider default
Images
supported

What it costs to run

WorkloadInputOutputCostPer 1,000 calls
Short chat turn1,000500$0.0076$7.60
Long document summary50,0002,000$0.1469$146.86
Agent step with tools20,0001,500$0.0658$65.83
1M in, 1M out1,000,0001,000,000$12.6600$12660.00

Calling it

const res = await client.chat.completions.create({
  model: "perplexity/sonar-reasoning-pro",
  messages: [{ role: "user", content: "Hello" }],
});