Sonar Deep Research
perplexity/sonar-deep-researchSonar Deep Research (perplexity/sonar-deep-research) is an AI model from Perplexity with a 128,000-token context window and 115,200 max output tokens, priced at $2.00/1M input and $8.00/1M output tokens. Available via the haimaker.ai OpenAI-compatible API.
Overview
Sonar Deep Research is a chat-based AI model developed by Perplexity, featuring a 128,000-token context window. It is optimized for reasoning tasks and priced at $2 per million input tokens and $8 per million output tokens. No details are available about its parameter count, architecture, or licensing.
Features & Capabilities
| Mode | Chat |
| Context Window | 128,000 tokens |
| Max Output | 115,200 tokens |
| Function Calling | Not supported |
| Vision | Not supported |
| Reasoning | Supported |
| Web Search | 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-deep-research",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
)
print(response.choices[0].message.content)Frequently Asked Questions
What is the context window of Sonar Deep Research?
Sonar Deep Research (perplexity/sonar-deep-research) has a 128,000-token context window and supports up to 115,200 output tokens per request.
How much does Sonar Deep Research cost?
Sonar Deep Research is priced at $2.00 per 1M input tokens and $8.00 per 1M output tokens when accessed via the haimaker.ai OpenAI-compatible API.
What features does Sonar Deep Research support?
Sonar Deep Research supports reasoning, web search.
How do I use Sonar Deep Research via API?
Send requests to https://api.haimaker.ai/v1/chat/completions with model "perplexity/sonar-deep-research" using any OpenAI-compatible SDK. Authentication uses a Bearer API key from https://app.haimaker.ai.
Use Sonar Deep Research with the haimaker API
Available via the haimaker.ai OpenAI-compatible API.