Perplexity: Sonar Deep Research

perplexity/sonar-deep-research · PerplexityUnmeasurable

Declared family: Unknown
Entered catalogue: 7 March 2025
Measurement: Deferred: measurement cost above the per-model cap
Evidence confidence: Unknown

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	Set up identically to 1 other listing, field for field	api_ceee0db7
How much it can read and write	Reads up to 128,000 tokens at onceOpenRouter's listing shows 115,200 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Whether it thinks before answering	Reasons when asked to	its own listing

Declared record

What the catalogue claims about this model

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Modalities: text->text
Declared tokenizer: Other
Prompt price: $2.00 / M tokens
Completion price: $8.00 / M tokens

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningtemperaturetop_ktop_pweb_search_options

defaults: {}

Catalogue entry

History

Every observation, kept as taken

7 March 2025Enters the OpenRouter catalogue with no declared family.