Sonar Medium Online API Pricing
As of October 10, 2026, Sonar Medium Online costs $0 per 1M input tokens and $1.80 per 1M output tokens on Perplexity. It has a 12,000-token context window and returns up to 12,000 tokens per response.
- Input
- $0 / 1M tokens
- Output
- $1.80 / 1M tokens
- Context window
- 12,000 tokens
- Max output
- 12,000 tokens
- Providers
- 1
- Added to LiteLLM
- March 2024
Sonar Medium Online pricing by provider
1 listing across 1 provider. 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-medium-online | $0 | $1.80 | 12K |
What Sonar Medium Online costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Perplexity | $0.90 |
Use Sonar Medium Online with LiteLLM
Call Sonar Medium Online 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-medium-online",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: sonar-medium-online
litellm_params:
model: perplexity/sonar-medium-online
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-medium-online",
"messages": [{"role": "user", "content": "Hello!"}]
}'Sonar Medium Online FAQ
How much does Sonar Medium Online cost?
Sonar Medium Online costs $0 per 1M input tokens and $1.80 per 1M output tokens on Perplexity.
What is the context window of Sonar Medium Online?
Sonar Medium Online has a 12,000-token context window and returns up to 12,000 tokens per response.
Which providers offer Sonar Medium Online?
Sonar Medium Online is available from Perplexity through LiteLLM, using the model name perplexity/sonar-medium-online.
How do I call Sonar Medium Online with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="perplexity/sonar-medium-online", 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.
When did LiteLLM add Sonar Medium Online?
Sonar Medium Online was added to LiteLLM's model price file in March 2024.
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.
Provider pages: Perplexity.
