Sonar Pro
Perplexity's search-augmented model. Combines LLM reasoning with real-time web search and citations.
200K
tokens
8K
tokens
$3
per 1M tokens
$15
per 1M tokens
65
tokens/sec
Feb 2025
2025-02-10
$9.00
per 1M tokens
8.7
quality per $
Capabilities
Benchmarks
Price vs Quality
Context Window in Context
- Codestral256K
- ▸ Sonar Pro200K
- o3 Mini200K
- o3200K
- Claude Opus 4200K
- Claude Sonnet 4200K
- Claude 3.5 Haiku200K
- GLM-5.1200K
ليس على بوابتنا بعد
لا تملك Swfte Connect مفتاحًا لـ Sonar Pro، لذا لا يوجد ما يمكن تشغيله هنا. أضف مفتاح المزوّد الخاص بك ثم استدعِ النموذج بالواجهة نفسها المستخدمة مع بقية نماذج هذا الدليل.
curl https://api.swfte.com/agents/v2/gateway/chat/completions \
-H "Authorization: Bearer $SWFTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity:sonar-pro",
"messages": [{"role": "user", "content": "Hello"}]
}'About Sonar Pro
Sonar Pro is a balanced AI model by Perplexity, released on February 10, 2025. It supports a context window of 200K tokens and can generate up to 8K output tokens.
At $3 per million input tokens and $15 per million output tokens, its blended cost of $9.00/1M tokens places it in the premium pricing tier. Its value score of 8.7 reflects the balance of quality and cost.
Using Sonar Pro with Swfte
Access Sonar Pro through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Sonar Pro in our AI Playground before integrating.