impulse

Sonar Deep Research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.

API id sonar-deep-researchReleased 7 Mar 2025 (Mar 2025)
Input / 1M
$2.00
at Perplexity
Output / 1M
$8.00
at Perplexity
Context window
128K
tokens
Max output
128K
tokens per reply
Hosts
1
1 listings
Released
Mar 2025
7 Mar 2025

Pricing

List prices at Perplexity, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$2.00$8.00
Web search
$5.00 per 1,000 searches

What it costs a month

At Perplexity list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$1,200
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$1,248
  • Coding agent1,000 requests a day, 40K in / 2K out$2,880
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$6,720
Use your own numbers

Where to run it

1 host serve Sonar Deep Research. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
PerplexityGateway
sonar-deep-research
$2.00 / $8.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Built-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Perplexity.

Smaller Perplexity models

  • Sonar Reasoning
    Perplexity · on Perplexity
    $1.00 / $5.00
    Has every key capability
    43% less

Other frontier labs

  • Gemini Omni 1.2 Flash
    Google · on Google AI Studio
    $1.50 / $9.00
    Has every key capability
    4% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    14% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    43% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    94% less

Open-weight picks

  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
    14% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    43% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    51% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    75% less

Call it

Using Perplexity's API.

Python
from litellm import completion

response = completion(
    model="perplexity/sonar-deep-research",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Sonar Deep Research cost?

On Perplexity, Sonar Deep Research costs $2.00 per million input tokens and $8.00 per million output tokens.

Which APIs offer Sonar Deep Research?

Sonar Deep Research runs on 1 API: Perplexity.

What is Sonar Deep Research's context window?

128K tokens, with up to 128K tokens in one reply.

Is Sonar Deep Research being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Sonar Deep Research?

Models that cost less and keep most of what it can do: Sonar Reasoning on Perplexity (43% less), Gemini Omni 1.2 Flash on Google AI Studio (4% less), Grok 4.7 on xAI (14% less) and Qwen3.8.2 4T A95B on DeepInfra (14% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Sonar Deep Research released?

Perplexity released it on 7 Mar 2025.

What is Sonar Deep Research's API model id?

Use sonar-deep-research with Perplexity.

Sources

Raw catalog entry for sonar-deep-research on Perplexity
{
  "citation_cost_per_token": 0.000002,
  "input_cost_per_token": 0.000002,
  "litellm_provider": "perplexity",
  "max_input_tokens": 128000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_reasoning_token": 0.000003,
  "output_cost_per_token": 0.000008,
  "search_context_cost_per_query": {
    "search_context_size_high": 0.005,
    "search_context_size_low": 0.005,
    "search_context_size_medium": 0.005
  },
  "supports_reasoning": true,
  "supports_web_search": true
}