How much does Sonar Deep Research cost?

Sonar Deep Research costs $2.00/M input tokens and $8.00/M output tokens, with separate rates for Web Search at $5.00/1K calls.

What is the context length of Sonar Deep Research?

Sonar Deep Research has a 128,000 token context window.

Does Sonar Deep Research support tool calling and structured outputs?

No. Sonar Deep Research does not accept tools, so function calling is unavailable. It does not support response_format, so JSON output is not enforced.

Which providers serve Sonar Deep Research?

Sonar Deep Research is served by 1 provider on OpenRouter: Perplexity.

What other text models does Perplexity have?

Decider Flash V1.3 (free), Decider V1.3 (free), Decider Flash V1.2 and 5 more are other text models from Perplexity.

When was Sonar Deep Research released?

Sonar Deep Research was released on March 7, 2025.

Perplexity: Sonar Deep Research

perplexity/sonar-deep-research

Compare

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 information. This enables comprehensive report generation across domains like finance, technology, health, and current events.

Notes on Pricing (Source)

Input tokens comprise of Prompt tokens (user prompt) + Citation tokens (these are processed tokens from running searches)
Deep Research runs multiple searches to conduct exhaustive research. Searches are priced at $5/1000 searches. A request that does 30 searches will cost $0.15 in this step.
Reasoning is a distinct step in Deep Research since it does extensive automated reasoning through all the material it gathers during its research phase. Reasoning tokens here are a bit different than the CoTs in the answer - these are tokens that we use to reason through the research material prior to generating the outputs via the CoTs. Reasoning tokens are priced at $3/1M tokens

Modalities

In / out price

$2 / $8per 1M

Context

128K

Released

Mar 7, 2025

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput


	$2.00	$8.00	109.5s	27 tok/s	62.50%

Input $2.00Output $8.00
27 tok/s62.50% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$2/M tokens

Output

$76.92/M tokens

Sonar Deep Research — Price history

Price history

No effective price data for this selection

		$2.00	$76.92	0.0%	100.0%

Effective in $2.00Effective out $76.92
Token share
100.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

94.81%

Availability over the last 3 days

Last 72 hours

Availability 94.81%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

92.92%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Not currently available through EU in-region routing. In-region routing docs

More models from Perplexity

Decider Flash V1.3 (free)

Decider Flash V1.3 is a decision model from Perplexity, a smaller, lower-cost sibling of Decider V1.3 with the same API contract. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It suits high-volume classification, routing, and moderation where application code thresholds the returned numbers rather than parsing a chat reply.

It also adds locate, served on the Extractions route, pulling text and list fields out of text state with source spans and confidences.

DecisionsFree

Decider V1.3 (free)

Decider V1.3 is a decision model from Perplexity, succeeding Decider V1.2. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply.

V1.3 also adds locate, served on the Extractions route: it pulls text and list fields out of text state and returns each value with its source span and a confidence. For a smaller, lower-cost option with the same contract, see Decider Flash V1.3.

DecisionsFree

Decider Flash V1.2

Decider Flash V1.2 is a 4B-parameter decision model from Perplexity, a smaller, lower-cost sibling of Decider V1.2 with the same API contract. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It suits high-volume classification, routing, and moderation where application code thresholds the returned numbers rather than parsing a chat reply.

Decisions$0.01 / $0

Decider V1.2

Decider V1.2 is a new 27B checkpoint of Perplexity's decision model, succeeding Decider V1.1 27B with the same API contract. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. For a smaller, lower-cost option with the same contract, see Decider Flash V1.2.

Decisions$0.02 / $0

Decider Flash Latest

This model always redirects to the latest model in the Decider Flash family.

Decisions

Decider Latest

This model always redirects to the latest model in the Decider family.

Decisions

Decider V1.1 27B

Decider V1.1 27B is a new checkpoint of Perplexity's decision model, succeeding Decider V1 27B with the same API contract. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 128 questions about the same content.

Decisions

Decider V1 27B

Decider V1 27B is a decision model from Perplexity. Instead of generating text, it reads content passed as state and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

Decisions

Embed V1 4B

pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval quality.

Embeddings$0.03/M tokens

Embed V1 0.6B

pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency embedding generation.

Embeddings$0.004/M tokens

Sonar Pro Search

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform.

Sonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.

Text200K context$3 / $15

Sonar Reasoning Pro

Note: Sonar Pro pricing includes Perplexity search pricing. See details here

Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.

Text128K context$2 / $8

Sonar Pro

Note: Sonar Pro pricing includes Perplexity search pricing. See details here

For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions.

Text200K context$3 / $15

R1 1776

R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem.

The model was tested on a multilingual dataset of over 1,000 examples covering sensitive topics to measure its likelihood of refusal or overly filtered responses. Evaluation Results Its performance on math and reasoning benchmarks remains similar to the base R1 model. Reasoning Performance

Perplexity: Sonar Deep Research

Providers