Sonar Reasoning
Sonar Reasoning is a text model from 
Vercel AI Gateway with a context window of 127K tokens and max output of 8K tokens. Pricing starts at 1.00 per million input tokens and 5.00 per million output tokens (cheapest at Perplexity).
Capabilities
✗ Vision✗ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | vercel_ai_gateway/perplexity/sonar-reasoning |
| Provider | Vercel AI Gateway |
| Provider ID | vercel_ai_gateway |
| Mode | Text |
| Canonical Name | sonar-reasoning |
| Context Window | 127K tokens |
| Max Output | 8K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.0010 | 1.00 |
| Output Tokens | 0.0050 | 5.00 |
Price Comparison by Provider
Compare prices for Sonar Reasoning across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
| Vercel AI Gateway | vercel_ai_gateway/perplexity/sonar-reasoning | 1.00 | 5.00 |
 Perplexity | perplexity/sonar-reasoning | 1.00 | 5.00 |
All Variants
All available versions, regions, and API endpoints for Sonar Reasoning.
Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| perplexity/sonar-reasoning | Perplexity | Text | 1.00 | 5.00 | 128K | N/A | no | no |
| vercel_ai_gateway/perplexity/sonar-reasoning | Vercel AI Gateway | Text | 1.00 | 5.00 | 127K | 8K | no | no |