perplexity/sonar-deep-research

Autonomous multi-step research reports with citations.

TextSearchReasoningsearchtools

Specifications

Context window: 127K
Max output tokens: 8,192
Released: 2025-03
Infra providers: 2
Throughput: 44 tok/s
Latency (TTFB, sample): 1800 ms
Capabilities: Supports tools

Pricing

per million tokens

Input

$2.00

Output

$8.00

Blended (3:1)

$3.50

Use this model

Works with any OpenAI SDK — same request shape, different model id.

curl https://api.lokarouter.id/v1/chat/completions \  -H "Authorization: Bearer sk-lkr-your-key" \  -H "Content-Type: application/json" \  -d '{    "model": "perplexity/sonar-deep-research",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Sample data for demonstration — connect your workspace for live stats.