Sonar
perplexity/sonarSonar (perplexity/sonar) is an AI model from Perplexity with a 127,072-token context window, priced at $1.00/1M input and $1.00/1M output tokens. Available via the haimaker.ai OpenAI-compatible API.
Overview
Sonar is a chat-based AI model developed by Perplexity, featuring vision capabilities. It supports a context window of 127,072 tokens, though its parameter count and maximum output length are unspecified. The model is priced at $1 per 1M tokens for both input and output. Details about its architecture and licensing remain unknown.
Features & Capabilities
| Mode | chat |
| Context Window | 127,072 tokens |
| Function Calling | Not supported |
| Vision | Supported |
| Reasoning | Not supported |
| Web Search | Not supported |
| Url Context | Not supported |
API Usage
from openai import OpenAI
client = OpenAI(
base_url="https://api.haimaker.ai/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="perplexity/sonar",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
)
print(response.choices[0].message.content)Frequently Asked Questions
What is the context window of Sonar?
Sonar (perplexity/sonar) has a 127,072-token context window.
How much does Sonar cost?
Sonar is priced at $1.00 per 1M input tokens and $1.00 per 1M output tokens when accessed via the haimaker.ai OpenAI-compatible API.
What features does Sonar support?
Sonar supports vision.
How do I use Sonar via API?
Send requests to https://api.haimaker.ai/v1/chat/completions with model "perplexity/sonar" using any OpenAI-compatible SDK. Authentication uses a Bearer API key from https://app.haimaker.ai.
Use Sonar with the haimaker API
OpenAI-compatible endpoint. Start building in minutes.