Back to models
deprecated

Perplexity: Sonar

perplexity/sonar

Prices

Input

$1.00 per 1M tokens

high
Output

$1.00 per 1M tokens

high
Per request

$12.00 per 1K requests

low
Web search (context size: high)

$0.012 per query

low
Web search (context size: low)

$0.005 per query

low
Web search (context size: medium)

$0.008 per query

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

16 sales channels for this model.
ChannelWhatPrice
OpenRouterInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
OpenRouter · perplexityInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
Query$0.005 per query
Other · aimlapiInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
Other · edenaiInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
Other · empiriolabsInput$2.40 per 1M tokens
Output$2.40 per 1M tokens
Other · heliconeInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
Other · kiloInput$1.00 per 1M tokens
Input (cache write)$0.0625 per 1M tokens
Output$2.50 per 1M tokens
Other · kymaInput$1.35 per 1M tokens
Output$1.35 per 1M tokens
Other · llmgatewayInput$0.25 per 1M tokens
Input (cache write)$0.25 per 1M tokens
Output$2.50 per 1M tokens
Other · llmgateway-providersInput$0.25 per 1M tokens
Input (cache write)$0.25 per 1M tokens
Output$2.50 per 1M tokens
Other · openrouterInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
Other · opperInput$1.00 per 1M tokens
Output$1.00 per 1M tokens
Other · perplexity-agentInput$0.25 per 1M tokens
Input (cached read)$0.0625 per 1M tokens
Output$2.50 per 1M tokens
Other · sap-ai-coreInput$1.00 per 1M tokens
Input (cache write)$0.25 per 1M tokens
Output$1.00 per 1M tokens
Other · vercelInput$0.25 per 1M tokens
Input (cache write)$0.0625 per 1M tokens
Output$2.50 per 1M tokens
Other · vercel-ai-gatewayInput$1.00 per 1M tokens
Output$1.00 per 1M tokens

Specifications

Provider
perplexity
Context window
127,072
Max output tokens
4,096
Open weights
no
Released
01/01/2024
Retires
no date announced
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
1 per 1M tokens, unchanged since 09/14/2026
Output
1 per 1M tokens, unchanged since 09/14/2026
Per request
12 per 1K requests, unchanged since 09/14/2026
Web search (context size: high)
0.012 per query, unchanged since 09/14/2026
Web search (context size: low)
0.005 per query, unchanged since 09/14/2026
Web search (context size: medium)
0.008 per query, unchanged since 09/14/2026

Last updated 11/19/2026, 01:12