Perplexity: Sonar Deep Research

perplexity/sonar-deep-research

Modalities: text->text
In / out price: $2 / $8
Context: 128K
Released: Mar 7, 2025
Knowledge cutoff: —

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...

ReasoningLong context

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
include_reasoning
Include reasoning
Include a reasoning summary in the response.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
presence_penalty
Presence penalty
Lowers the chance of any token that has already appeared.
reasoning
Reasoning
Enable or configure reasoning. The fields differ by model.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.
top_k
Top-K
Sample only from the K most likely tokens.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.
web_search_options
Web search
Let a search-capable model look up the web before answering.

Models Perplexity

Perplexity: Sonar Deep Research

perplexity/sonar-deep-research

Try this model

Modalities: text->text
In / out price: $2 / $8
Context: 128K
Released: Mar 7, 2025
Knowledge cutoff: —

ReasoningLong context

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
include_reasoning
Include reasoning
Include a reasoning summary in the response.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
presence_penalty
Presence penalty
Lowers the chance of any token that has already appeared.
reasoning
Reasoning
Enable or configure reasoning. The fields differ by model.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.
top_k
Top-K
Sample only from the K most likely tokens.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.
web_search_options
Web search
Let a search-capable model look up the web before answering.