Perplexity Sonar Deep Research API Pricing

Perplexity · released Feb 1, 2025 · 128K context · API model ID sonar-deep-research

Perplexity Sonar Deep Research by Perplexity API pricing: $2.00 per 1M input tokens and $8.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).

Prices

Perplexity Sonar Deep Research prices, USD per 1M tokens
PriceUSD per 1M tokens
Input$2.00
Output$8.00
Cache readNot published
Cache writeNot published
Reasoning output$3.00

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

$1,800

per month

per day
$60.00
per request
$0.006

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$1,800/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day$3,000/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input$3,480/mo

Context and capabilities

Context
128,000 tokens
Max output
32,768 tokens
Input
text
Output
text
Knowledge cutoff
January 2025
Open weights
No
Tool calling
No
Reasoning
Yes
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 Perplexity Sonar Deep Research cost per month?
For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Perplexity Sonar Deep Research costs about $1,800 per month at Perplexity's list prices ($2.00 per 1M input tokens, $8.00 per 1M output tokens).
Does Perplexity Sonar Deep Research support prompt caching?
No cache read price is published for Perplexity Sonar Deep Research.
How long is Perplexity Sonar Deep Research's context window?
Perplexity Sonar Deep Research accepts up to 128,000 tokens (128K) of context and returns up to 32,768 tokens per response.