RentGPU RentGPU
GPU finden →
by Perplexity

Perplexity: Sonar Deep Research.

text closed 128K ctx
Cheapest input
$2.0/M
on OpenRouter
Cheapest output
$8.0/M
on OpenRouter
Fastest
0 tok/s
on OpenRouter
Hosted equiv.
~$2.88/hr
@ 100 tok/s on OpenRouter

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 gathe

Hosted API only

No self-host path — closed weights.

Perplexity: Sonar Deep Research's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $2.0 $8.0 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 0.0 — 10005 ms
FAQ

Frequently asked.

How do I run Perplexity: Sonar Deep Research?
Perplexity: Sonar Deep Research is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Perplexity: Sonar Deep Research?
Perplexity: Sonar Deep Research is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Perplexity: Sonar Deep Research?
API pricing starts at $2.0/M input tokens and $8.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Perplexity: Sonar Deep Research open-source or proprietary?
Perplexity: Sonar Deep Research is a proprietary model from Perplexity. Access is API-only — there are no public weights to download.