tokenstat
tokenstat

Perplexity Sonar Reasoning Pro

perplexity/sonar-reasoning-pro · rates as of · Benchmarks · Plans · Calculator

Web-grounded reasoning model for multi-step research and cited answers

Cheapest input
$2
$/MTok · models.dev
Cheapest output
$8
$/MTok
Context
128K
tokens
Offers
8
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestperplexity/sonar-reasoning-proKilo Gateway$2$8$0128K
OpenRouterperplexity/sonar-reasoning-proOpenRouter$2$8$0128K
models.devsonar-reasoning-proPerplexity$2$8$0.2128K
models.devsonar-reasoning-proHelicone$2$8$0127K
models.devsonar-reasoning-proLLM Gateway$2$8$0128K
LiteLLMsonar-reasoning-pro$2$8$0.2
LiteLLMvercel_ai_gateway/perplexity/sonar-reasoning-pro$2$8$0.2
models.devsonar-reasoning-proNanoGPT$2.01$8$0127K

Capabilities

  • Reasoning
  • Attachments
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2025-09-01Released: 2025-03-07Family: sonar-reasoning

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash