Sonar Deep Research
sonar-deep-research
Last refreshed 2026-05-15. Next refresh: weekly.
Sonar Deep Research is worth evaluating for rag, long context, and classification when its provider route and context window match the workload.
Decision context: RAG task fit, 2 tracked provider routes, and research from 2026-05-15.
Use it for
- Teams evaluating rag, long context, and classification
- Workloads that can use a 128K context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
Cheapest output
$8.00
OpenRouter per 1M tokens
Provider routes
2
Tracked API hosts
Quality / dollar
Unknown
No task benchmark coverage yet
Freshness
2026-05-15
Researched 6d ago
Top use-case fit
RAG
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Classification
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 2| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $2.00 | $8.00 | Serverless |
| Perplexity Labs | $2.00 | $8.00 | Serverless |
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
About
Expert-level Perplexity research model conducting exhaustive multi-step searches and generating comprehensive reports. Additional fees: $5/1K searches, $2/MTok citations, $3/MTok reasoning tokens. Supports async API with 7-day TTL and reasoning_effort parameter (low/medium/high).
Sonar Deep Research has a 128K-token context window.
Sonar Deep Research input tokens at $2/1M, output at $8/1M.
Capabilities
Created by
Developing AI for complex problem-solving.