Sonar Reasoning Pro
Summary
Sonar Reasoning Pro is a proprietary language model from Perplexity, released on 1 Jan 2024. It accepts text and images and generates text, with a 128K-token context window and up to 4K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $2 per million input tokens and $8 per million output tokens (OpenRouter), across 1 provider we track. Perplexity has deprecated this model.
Web-grounded Sonar for multi-step research questions that need cited reasoning
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Perplexity |
|---|---|
| Release date | 1 Jan 2024 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 128K (128,000 tokens) [models.dev] |
| Max output | 4K tokens [models.dev] |
| Knowledge cutoff | 1 Sept 2025 [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | No [models.dev] |
Sonar Reasoning Pro API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter perplexity/sonar-reasoning-pro | $2 | $8 | – | 128K | OpenRouter, 19 Nov 2026 |
Frequently asked questions
What is the context window of Sonar Reasoning Pro?
Sonar Reasoning Pro has a context window of 128,000 tokens (128K) and can generate up to 4,096 tokens in a single response, according to models.dev.
How much does the Sonar Reasoning Pro API cost?
Sonar Reasoning Pro is listed from $2 per million input tokens and $8 per million output tokens (OpenRouter). Prices last verified 19 Nov 2026.
Is Sonar Reasoning Pro open source?
No. Sonar Reasoning Pro is a proprietary model; Perplexity has not released its weights. It is available through APIs including OpenRouter.
When was Sonar Reasoning Pro released?
Perplexity released Sonar Reasoning Pro on 1 Jan 2024, according to models.dev.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Mistral Large | Mistral AI | 26 Feb 2024 | 128K | $2 | $6 | Closed |
| GPT-4o (2024-08-06) | OpenAI | 6 Aug 2024 | 128K | $2.50 | $10 | Closed |
| Qwen Max | Alibaba (Qwen) | 3 Apr 2024 | 33K | $1.60 | $6.40 | Closed |
| Pixtral Large (25.02) | Mistral AI | 8 Apr 2025 | 128K | $2 | $6 | Closed |
| Claude 3 Haiku | Anthropic | 13 Mar 2024 | 200K | – | – | Closed |
| GPT-3.5 Turbo 16k | OpenAI | 28 Aug 2023 | 16K | $3 | $4 | – |
Change history
- Status changed from active to deprecated
- No longer listed on perplexity