Perplexity: Sonar Deep Research
perplexity/sonar-deep-researchSonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.
Modalities
In / out per 1M$2.00 / $8.00
Context125K
ReleasedMar 7, 2025
Providers
1 provider serves this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Perplexity | $2.00 | $8.00 | Variable | 155.53s | 45 tps | 95.24% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Sonar Deep Research in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Sonar Deep Research costs pay-as-you-go elsewhere, not what you pay here.
Input
$2.00
per 1M tokens
Output
$8.00
per 1M tokens
Cache read
—
not published
Included in every pass
Sonar Deep Research is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s200.0s400.0s600.0s800.0s
Oct 12, 8 AMOct 12, 9 AMOct 12, 10 AMOct 12, 12 PMOct 13, 7 AMOct 13, 9 AMOct 13, 10 AMOct 13, 11 AMOct 13, 12 PMOct 13, 1 PMOct 13, 2 PMOct 13, 3 PMOct 14, 9 AM
Median 90th percentile 99th percentile
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 12, 8 AMOct 12, 9 AMOct 12, 10 AMOct 12, 12 PMOct 13, 7 AMOct 13, 9 AMOct 13, 10 AMOct 13, 11 AMOct 13, 12 PMOct 13, 1 PMOct 13, 2 PMOct 13, 3 PMOct 14, 9 AM
Median 90th percentile 99th percentile
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 67.65%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 69.6%
100% 69% 40% 10%
Oct 13, 2:50 PMNow
Apps
Tools that most often run Sonar Deep Research, by tokens this week.
Activity
416.4M tokens processed market-wide in the last month.
010.0M20.0M30.0M40.0M
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Sonar Deep Research?
perplexity/sonar-deep-research. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Sonar Deep Research hold?
128,000 tokens per request, of which up to 115,200 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Sonar Deep Research cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $2.00 per 1M input tokens and $8.00 per 1M output tokens.
Who built Sonar Deep Research?
Perplexity, in the Sonar family.
Explore
Other models your pass can call.
