Sonar Deep Research
Perplexity Sonar Deep Research — pricing, 128k context window, API cost calculator and alternatives.
By Perplexity
Specs
- Provider
- Perplexity
- Slug
- perplexity/sonar-deep-research
- Capabilities
- text-only
Pricing freshness
- Tier
- standard
- Currency
- USD
- As of
- 2026-05-08 17:08 UTC
Pricing history
Tracking Sonar Deep Research pricing since 2026-05-08. We'll plot the chart here once it changes.
Quickstart — call Sonar Deep Research from your app
curl https://openrouter.ai/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-d '{
"model": "perplexity/sonar-deep-research",
"messages": [{"role": "user", "content": "Hello!"}]
}'Official docs: https://openrouter.ai/docs
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=os.environ["OPENROUTER_API_KEY"],
)
resp = client.chat.completions.create(
model="perplexity/sonar-deep-research",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Official docs: https://openrouter.ai/docs
// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const resp = await client.chat.completions.create({
model: "perplexity/sonar-deep-research",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Official docs: https://openrouter.ai/docs
Related models
Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.
Frequently asked questions
What is Sonar Deep Research?
Sonar Deep Research is a large language model API from Perplexity with a 128k-token context window. It costs $2 per 1M input tokens and $8 per 1M output tokens.
How much does Sonar Deep Research cost?
Sonar Deep Research is priced at $2 per 1M input tokens and $8 per 1M output tokens via the Perplexity API. A 50/50 input/output workload of 1M total tokens costs about $5.
What is the context window of Sonar Deep Research?
Sonar Deep Research supports up to 128k tokens of context per request — roughly 256 pages of English text or 16000 lines of code at a typical density.
Does Sonar Deep Research support vision, tool use, or JSON mode?
Sonar Deep Research is a text-only model — it does not support vision, tool use, or structured JSON mode.
Who makes Sonar Deep Research?
Sonar Deep Research is built and operated by Perplexity. Pricing, context window, and capabilities on this page are refreshed nightly from Perplexity's public catalog.
Can I self-host Sonar Deep Research?
Sonar Deep Research is API-only — its weights are not publicly distributed by Perplexity, so it cannot be self-hosted today.