Research model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.
PerplexityResearch & Search128K contextProprietary EndpointResearch model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.
perplexity-deep-researchPOST /v1/chat/completionsPOST /v1/responsesPOST /v1/messagesPOST /v1/searchLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Perplexity Deep Research serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id perplexity-deep-research. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity-deep-research",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="perplexity-deep-research",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Perplexity Deep Research API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| temperature | number | 0.2 | 0 to 2 | Sampling temperature. 0 = deterministic, 2 = maximum randomness. |
| max_tokens | number | 16384 | 1 to 65536 | Maximum tokens in the response. |
| reasoning_effort | enum | high | low, medium, high | Level of reasoning depth. Higher effort = more thorough analysis but slower. |
| search_mode | enum | default | default | Filter search results by source type. Academic = scholarly papers, SEC = financial filings. |
| search_domain_filter | string | - | - | Comma-separated domains. Prefix with '-' to exclude. Max 20. |
| search_language_filter | string | - | - | Comma-separated ISO 639-1 codes (2 letters). Max 10. |
| search_after_date_filter | string | - | - | Only include sources published after this date. Use YYYY-MM-DD or natural language. |
| search_before_date_filter | string | - | - | Only include sources published before this date. Use YYYY-MM-DD or natural language. |
| search_recency_filter | enum | none | none, hour, day, week, month, year | Relative time filter. Cannot be combined with specific dates. |
| last_updated_after_filter | string | - | - | Only include sources last updated after this date. |
| last_updated_before_filter | string | - | - | Only include sources last updated before this date. |
| country | string | - | - | Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country. |
| region | string | - | - | State or province name for location bias. |
| city | string | - | - | City name for location bias. |
Long-running multi-step retrieval and reasoning. Pricing splits Input / Output / Citation / Reasoning tokens plus per-query search charge.
On EmpirioLabs, Perplexity Deep Research is billed pay as you go: Input $4.80 per 1M prompt tokens; Output $19.00 per 1M generated tokens; Citation Tokens $4.80 per 1M tokens. The live rate card on this page always matches what the API charges.
Perplexity Deep Research supports a 128K-token context window.
Yes. Perplexity Deep Research serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to perplexity-deep-research.
Yes. The EmpirioLabs playground runs Perplexity Deep Research in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
