# Sonar API Pricing

As of October 10, 2026, Sonar costs $1.00 per 1M input tokens and $1.00 per 1M output tokens on Perplexity. Across 2 providers on LiteLLM, the input price ranges from $0.25 to $1.00. It has a 128,000-token context window and returns up to 8,000 tokens per response.

- Page: https://models.litellm.ai/models/sonar
- Lab: Perplexity
- LiteLLM model name: `perplexity/sonar`
- Context window: 128,000 tokens
- Max output: 8,000 tokens
- Added to LiteLLM: February 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Perplexity | `perplexity/sonar` | $1.00 | $1.00 | – | – | – | 128K |
| Perplexity | `perplexity/perplexity/sonar` | $0.25 | $2.50 | $0.0625 | – | – | – |
| Vercel AI Gateway | `vercel_ai_gateway/perplexity/sonar` | $1.00 | $1.00 | – | – | – | 127K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Perplexity: $2.50
- Vercel AI Gateway: $2.50

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Perplexity: $10.20
- Vercel AI Gateway: $10.20

## Features

Supported: Function calling, Web search.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="perplexity/sonar",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Sonar cost?

Sonar costs $1.00 per 1M input tokens and $1.00 per 1M output tokens on Perplexity. Across 2 providers on LiteLLM, the input price ranges from $0.25 to $1.00.

### What is the context window of Sonar?

Sonar has a 128,000-token context window and returns up to 8,000 tokens per response.

### Which providers offer Sonar?

Sonar is available from 2 providers through LiteLLM: Perplexity and Vercel AI Gateway. The lowest price is on Perplexity.

### How do I call Sonar with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="perplexity/sonar", 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 support?

Sonar supports function calling and web search.

### When did LiteLLM add Sonar?

Sonar was added to LiteLLM's model price file in February 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json