Side-by-side comparison
Claude 3.7 Sonnet (thinking) vs Sonar Pro Search
Anthropic
Claude 3.7 Sonnet (thinking)
👁 Vision
🔧 Tools
Input / 1M
$3.0000
Output / 1M
$15.0000
Perplexity
Sonar Pro Search
👁 Vision
Input / 1M
$3.0000
Output / 1M
$15.0000
| Claude 3.7 Sonnet (thinking) | Sonar Pro Search | |
|---|---|---|
| Provider | Anthropic | Perplexity |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 200,000 | 200,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools | vision |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 3.0000 | 3.0000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 15.0000 | 15.0000 |
Frequently asked questions
Which is cheaper, Claude 3.7 Sonnet (thinking) or Sonar Pro Search?
Claude 3.7 Sonnet (thinking) is cheaper than Sonar Pro Search on a 50/50 input/output blend by about $0 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
What is the difference between Claude 3.7 Sonnet (thinking) and Sonar Pro Search?
Claude 3.7 Sonnet (thinking) comes from Anthropic; Sonar Pro Search comes from Perplexity. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.