Sonar Reasoning API Pricing
As of October 10, 2026, Sonar Reasoning costs $1.00 per 1M input tokens and $5.00 per 1M output tokens on Perplexity. It has a 128,000-token context window and returns up to 8,000 tokens per response.
- Input
- $1.00 / 1M tokens
- Output
- $5.00 / 1M tokens
- Context window
- 128,000 tokens
- Max output
- 8,000 tokens
- Providers
- 2
- Added to LiteLLM
- May 2025
Sonar Reasoning pricing by provider
2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Perplexity | perplexity/sonar-reasoning | $1.00 | $5.00 | 128K |
| Vercel AI Gateway | vercel_ai_gateway/perplexity/sonar-reasoning | $1.00 | $5.00 | 127K |
Other Sonar Reasoning prices on Perplexity
| Web search | $8.00 per 1K searches |
What Sonar Reasoning costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Perplexity | $4.50 |
| Vercel AI Gateway | $4.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Perplexity | $11.00 |
| Vercel AI Gateway | $11.00 |
Sonar Reasoning features
- Reasoning
- Web search
Use Sonar Reasoning with LiteLLM
Call Sonar Reasoning through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="perplexity/sonar-reasoning",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: sonar-reasoning
litellm_params:
model: perplexity/sonar-reasoning
api_key: os.environ/PERPLEXITYAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "sonar-reasoning",
"messages": [{"role": "user", "content": "Hello!"}]
}'Sonar Reasoning FAQ
How much does Sonar Reasoning cost?
Sonar Reasoning costs $1.00 per 1M input tokens and $5.00 per 1M output tokens on Perplexity.
What is the context window of Sonar Reasoning?
Sonar Reasoning has a 128,000-token context window and returns up to 8,000 tokens per response.
Which providers offer Sonar Reasoning?
Sonar Reasoning is available from 2 providers through LiteLLM: Perplexity and Vercel AI Gateway.
How do I call Sonar Reasoning with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="perplexity/sonar-reasoning", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Sonar Reasoning support?
Sonar Reasoning supports reasoning and web search.
When did LiteLLM add Sonar Reasoning?
Sonar Reasoning was added to LiteLLM's model price file in May 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.
LiteLLM docs: Perplexity, Vercel AI Gateway.
Provider pages: Perplexity, Vercel AI Gateway.