tokenstat
tokenstat

Perplexity: Sonar Deep Research

perplexity/sonar-deep-research · rates as of · Benchmarks · AI plans · Calculator

Sonar search model for current answers, retrieval, and citation-backed chat

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

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestperplexity/sonar-deep-researchKilo Gateway$2$8$0128K
models.devperplexity/sonar-deep-researchLLMTR$2$8$0128K
OpenRouterperplexity/sonar-deep-researchOpenRouter$2$8$0.2128K
models.devsonar-deep-researchPerplexity$2$8$0.2128K
models.devsonar-deep-researchHelicone$2$8$0127K
models.devsonar-deep-researchSAP AI Core$2$8$0128K
models.devperplexityai/sonar-deep-researchEden AI$2$8$0128K
LiteLLMsonar-deep-researchN/A$2$8$0.2N/A

Capabilities

  • Reasoning
  • In: text
  • Out: text
Knowledge cutoff: 2025-01Released: 2025-03-07Family: sonar-deep-research

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.