Seedance 2.0 | Special Offer ✦ 10% OFF NOW
P

perplexity/sonar-deep-research

perplexity/sonar-deep-research

128,000 context · $2.00/M input tokens · $8.00/M output tokens

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Cennik

Płać za użycie

Bez kosztów początkowych, płacisz tylko za to, czego używasz

Wejście$2.00 / M Tokens
Wyjście$8.00 / M Tokens

Użycie API

Użyj poniższych przykładów kodu, aby zintegrować się z naszym API:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="perplexity/sonar-deep-research",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

Wprowadzenie do modelu

Perplexity sonar-deep-research

perplexity sonar-deep-research


Why It Looks Great

  • Large Language Model architecture for efficient processing
  • 128000 context window for long document handling
  • Competitive pricing at $2.2/$8.8 per million tokens

Key Features

  • Context Window: 128000 tokens
  • Max Output: 4096 tokens
  • Vision: Supported
  • Function Calling: Supported

Specifications

SpecificationValue
ProviderPerplexity
Model TypeLarge Language Model (LLM)
ArchitectureN/A
Context Window128000 tokens
Max Output4096 tokens
InputText
OutputText
VisionSupported
Function CallingSupported

Pricing

Token TypeCost per Million Tokens
Input$2.2
Output$8.8

How to Use

  1. Write your prompt — describe the task, provide context, and specify desired output format.
  2. Submit — the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: perplexity/sonar-deep-research


API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="perplexity/sonar-deep-research",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "perplexity/sonar-deep-research",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: perplexity/sonar-deep-research
  • Provider: Perplexity

Info

Dostawcaperplexity
Typllm

Obsługiwane funkcje

Wejście
Tekst
Wyjście
Tekst
Kontekst128,000
Maks. wyjście4,096
Vision-
Function Calling-

Przewodnik dostępu do API

Base URLhttps://llm.wavespeed.ai/v1
API Endpointchat/completions
ID modeluperplexity/sonar-deep-research

perplexity/sonar-deep-research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Wejście

$2 /M

Wyjście

$8 /M

Kontekst

128K

Maks. wyjście

4K

Wypróbuj perplexity/sonar-deep-research w WaveSpeedAI

Uzyskaj dostęp do perplexity/sonar-deep-research przez nasze ujednolicone API — kompatybilne z OpenAI, bez zimnych startów, przejrzyste ceny.

Otwórz Playground