Skip to main content

Sonar Deep Research

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

Input / output price
$2.00 / $8.00 per 1M
Context
919K tokens
Released
Feb 25, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "sonar-deep-research".

Read docs

Providers

2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
EmpirioLabsempiriolabs/sonar-deep-research
$4.80/M$19.00/M
OpenRouteropenrouter/sonar-deep-research
$2.00/M$8.00/M

Is a provider down? OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input
$3.40 per 1M
Average output
$13.50 per 1M
Average cache read
$4.80 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$4.80/MEmpirioLabsLowest$2.00/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Response latency

Lower is better

2.1sacross providers

Faster than 49% of the other 780 models on the gateway

Benchmarks

6 published scores from 1 source, each linked to where it was published.

Published scores

BenchmarkScore
DRACO Presentation Quality (Opus 4.6 base)r2cdn.perplexity.ai90.3%
DRACO Breadth & Depth (Opus 4.6 base)r2cdn.perplexity.ai73.1%
DRACO Pass Rate (Opus 4.6 base)r2cdn.perplexity.ai72.8%
DRACO Normalized Score (Opus 4.6 base)r2cdn.perplexity.ai70.5%
DRACO Factual Accuracy (Opus 4.6 base)r2cdn.perplexity.ai67.9%
DRACO Citation Quality (Opus 4.6 base)r2cdn.perplexity.ai64.6%

Apps

Use Sonar Deep Research in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Sonar Deep Research FAQ

Short answers, built from the data on this page.

Sonar Deep Research is a model from Perplexity, released on Feb 25, 2025. 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.

On the Respan gateway, Sonar Deep Research costs from $2.00 per 1M input tokens and $8.00 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 2 providers, it costs $3.40 per 1M input tokens and $13.50 per 1M output tokens.

Sonar Deep Research is available through 2 providers: EmpirioLabs and OpenRouter.

Sonar Deep Research accepts up to 919K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "sonar-deep-research". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Sonar Deep Research has 6 published benchmark scores, including DRACO Presentation Quality (Opus 4.6 base) 90.3%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.