Sonar Pro API Pricing

Perplexity · released Jan 1, 2024 · 200K context · API model ID sonar-pro

Sonar Pro by Perplexity API pricing: $3.00 per 1M input tokens and $15.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).

Prices

Sonar Pro prices, USD per 1M tokens
PriceUSD per 1M tokens
Input$3.00
Output$15.00
Cache readNot published
Cache writeNot published

Perplexity's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation

Estimated monthly cost

$3,150

per month

per day
$105.00
per request
$0.0105

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.

Compare this workload across models

Monthly cost by workload

WorkloadPer month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day$3,150/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day$4,725/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input$5,400/mo

Context and capabilities

Context
200,000 tokens
Max output
8,192 tokens
Input
text, image
Output
text
Knowledge cutoff
Sep 1, 2025
Open weights
No
Tool calling
No
Reasoning
No
Structured outputs
No

Capabilities and limits as listed by models.dev.

Similarly priced models

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does Sonar Pro cost per month?
For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Sonar Pro costs about $3,150 per month at Perplexity's list prices ($3.00 per 1M input tokens, $15.00 per 1M output tokens).
Does Sonar Pro support prompt caching?
No cache read price is published for Sonar Pro.
How long is Sonar Pro's context window?
Sonar Pro accepts up to 200,000 tokens (200K) of context and returns up to 8,192 tokens per response.