Sonar Reasoning Pro
sonar-reasoning-pro- Context window
- 128,000 tokens
- Maximum output
- Not documented
- Input price
- $2 per 1M tokens
- Output price
- $8 per 1M tokens
- Modalities
- text
Last verified · Source ↗
Official description
Learn about Sonar Reasoning Pro for advanced multi-step reasoning, including pricing and API usage.
Read the official model reference ↗.
Where this model fits
sonar-reasoning-pro is part of the Perplexity API catalog. Its documented modalities are text. Choose it against the request format, output requirements and operational limits of your application.
The source metadata identifies support for search. Confirm endpoint-specific parameters in the official reference before integrating that capability.
The source metadata identifies support for search-augmented. Confirm endpoint-specific parameters in the official reference before integrating that capability.
For a repeatable evaluation, use representative requests, inspect structured output or tool calls, and log latency and usage in your own account. Catalog metadata establishes compatibility; it does not measure answer quality on your workload. Start from the provider guide for authentication and endpoint setup.
Current pricing
| Model | Price type | USD | Unit | Tier | Region | Source |
|---|---|---|---|---|---|---|
| Sonar Reasoning Pro | Input | $2 | per 1M tokens | Standard | See source | Official source ↗ |
| Sonar Reasoning Pro | Output | $8 | per 1M tokens | Standard | See source | Official source ↗ |
| Sonar Reasoning Pro | Per Request | $0.014 | per request | high search context | See source | Official source ↗ |
| Sonar Reasoning Pro | Per Request | $0.006 | per request | low search context | See source | Official source ↗ |
| Sonar Reasoning Pro | Per Request | $0.01 | per request | medium search context | See source | Official source ↗ |
Last verified · Source ↗
Estimate request, daily and monthly usage in the API cost calculator.
Rate limits and availability
| Model or scope | Tier | Metric | Limit | Notes | Source |
|---|---|---|---|---|---|
Sonar Reasoning Prosonar-reasoning-pro | Tier 0 | RPM | 50 | Sonar API | Official source ↗ |
Sonar Reasoning Prosonar-reasoning-pro | Tier 1 | RPM | 150 | Sonar API | Official source ↗ |
Sonar Reasoning Prosonar-reasoning-pro | Tier 2 | RPM | 500 | Sonar API | Official source ↗ |
Sonar Reasoning Prosonar-reasoning-pro | Tier 3 | RPM | 1,000 | Sonar API | Official source ↗ |
Sonar Reasoning Prosonar-reasoning-pro | Tier 4 | RPM | 4,000 | Sonar API | Official source ↗ |
Sonar Reasoning Prosonar-reasoning-pro | Tier 5 | RPM | 4,000 | Sonar API | Official source ↗ |
Last verified · Source ↗
Account-specific capacity may differ. Check the provider rate-limit guide and the free-tier conditions.
Three alternatives to compare
These alternatives share a documented modality and have the closest combination of input price and context size in the current catalog. This is a specification comparison, not a quality benchmark.
| Model | Provider | Input / 1M tokens | Context |
|---|---|---|---|
| Mistral Large | OpenRouter | $2 | 128,000 |
| Perplexity: Sonar Deep Research | OpenRouter | $2 | 128,000 |
| Perplexity: Sonar Reasoning Pro | OpenRouter | $2 | 128,000 |
Use the exact identifier in Python
This identifier fragment belongs in the authenticated request described in the provider Python tutorial. The tutorial covers the correct SDK, endpoint, environment variable and response shape.
model = "sonar-reasoning-pro"
# Pass model to the provider-specific request in the tutorial.Recent changes
- Perplexity · Sonar Reasoning Pro — MetadataRecord updated; consult the linked source for details. → Record updated; consult the linked source for details.Source ↗
- Perplexity · Sonar Reasoning Pro — ValueNot previously recorded → Tier: Tier 5 · Metric: RPM · Value: 4000 · Notes: Sonar APISource ↗
- Perplexity · Sonar Reasoning Pro — ValueNot previously recorded → Tier: Tier 4 · Metric: RPM · Value: 4000 · Notes: Sonar APISource ↗
- Perplexity · Sonar Reasoning Pro — ValueNot previously recorded → Tier: Tier 3 · Metric: RPM · Value: 1000 · Notes: Sonar APISource ↗
- Perplexity · Sonar Reasoning Pro — ValueNot previously recorded → Tier: Tier 2 · Metric: RPM · Value: 500 · Notes: Sonar APISource ↗
- Perplexity · Sonar Reasoning Pro — ValueNot previously recorded → Tier: Tier 1 · Metric: RPM · Value: 150 · Notes: Sonar APISource ↗
- Perplexity · Sonar Reasoning Pro — ValueNot previously recorded → Tier: Tier 0 · Metric: RPM · Value: 50 · Notes: Sonar APISource ↗
- Perplexity · Sonar Reasoning Pro — Amount UsdNot previously recorded → Price category: per_request · USD: 0.014 · Unit: per request · Tier: high search contextSource ↗
- Perplexity · Sonar Reasoning Pro — Amount UsdNot previously recorded → Price category: per_request · USD: 0.01 · Unit: per request · Tier: medium search contextSource ↗
- Perplexity · Sonar Reasoning Pro — Amount UsdNot previously recorded → Price category: per_request · USD: 0.006 · Unit: per request · Tier: low search contextSource ↗
Subscribe to the changelog RSS feed
Frequently asked questions
What is the exact API model identifier?
sonar-reasoning-pro exactly as shown in the provider model reference. Display names are not interchangeable with API identifiers.How much does this model cost?
How much input can the model accept?
Can I use a free tier?
Where do these model facts come from?
Sources
Last verified · Source ↗