Perplexity Sonar Deep Research Official Specifications, Pricing & Benchmarks
Perplexity Sonar Deep Research (sonar-deep-research) by Perplexity, released 2025-02-01, featuring 128,000 context window, 32,768 max output tokens, and Text input.
📋 Perplexity Sonar Deep Research Official API & System Card Specifications
Verified against official Perplexity developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- sonar-deep-research
- Release Date
- 2025-02-01
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- 部分支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 128,000 tokens (128K)
- Max Output Tokens
- 32,768 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 2
- Cached Input / 1M
- $ 0.4 -80%
- Output / 1M Tokens
- $ 8
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
💡 Custom temperature disabled in reasoning mode; adjust reasoning effort/budget instead.
Closest Self-Hostable Open-Weight Alternatives to Perplexity Sonar Deep Research
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Perplexity Sonar Deep Research open-source or proprietary?
Perplexity Sonar Deep Research (sonar-deep-research) is a proprietary commercial model by Perplexity. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Perplexity Sonar Deep Research?
Perplexity Sonar Deep Research supports 128K input context and 32,768 max output tokens, priced at $2/1M input ($0.4/1M cached) and $8/1M output.