v0.1.0-beta

OpenAPI 3.1.0

Perplexity Sonar Deep Research

Felo API Support

MIT

Server

https://openapi.felo.ai

Client Libraries

Shell Curl

Perplexity API

Generate answers and research reports with web citations.

Perplexity API Operations

post/v1/beta/perplexity/sonar-deep-research

Perplexity Sonar Deep Research

Generate a research report using multiple web searches and cited sources. model and messages are required; use model sonar-deep-research for this endpoint. This public contract covers non-streaming JSON responses with stream false. Research can take several minutes and may exceed gateway or client timeouts. Read choices[].message.content, citations and search_results for the report and its sources. usage is not a Felo credit charge.

Body·ChatCompletionRequest

required

application/json

messages
Type: array object[]
required

A list of messages comprising the conversation so far.
- content
  Type: string
  required
  
  The content of the message.
- role
  Type: string enum
  required
  
  The role of the message author.
  
  values
  system
  user
  assistant
model
Type: string enum
required

The Sonar model to use.
values
- sonar
- sonar-pro
- sonar-reasoning-pro
- sonar-deep-research
frequency_penalty
Type: number
min:
0
max:
2

Penalizes new tokens based on their existing frequency in the text so far. Positive values decrease the likelihood of repeating the same line verbatim.
max_tokens
Type: integer

The maximum number of tokens to generate in the response.
presence_penalty
Type: number
min:
-2
max:
2

Penalizes new tokens based on whether they appear in the text so far. Positive values increase the likelihood of talking about new topics.
return_citations
Type: boolean

Whether to return citations and search results in the response.
search_context
Type: string enum

Controls how much search context to use. Affects per-request cost.
values
- low
- medium
- high
search_domain_filter
Type: array string[]

Limit search to specific domains.
search_recency_filter
Type: string enum

Filter search results by recency.
values
- month
- week
- day
- hour
stream
Type: boolean enum
const:
false

Only non-streaming JSON responses are covered by this public contract. Set false.
values
- false
temperature
Type: number
min:
0
max:
2

Sampling temperature between 0 and 2. Lower values make output more focused and deterministic.
top_k
Type: integer
min:
0
max:
2048

The number of tokens to keep for top-k filtering.

top_p
Type: number
min:
0
max:
1

Nucleus sampling parameter. The model considers tokens with top_p probability mass.

Responses

200
Type: object · ChatCompletionResponse

Successful response with AI answer and citations
choices
Type: array object[]
finish_reason
Type: string enum
values
stop
length
index
Type: integer

Integer numbers.

message
Type: object
content
Type: string

The AI-generated answer, with inline citation references like [1][2].

role
Type: string
citations
Type: array string[]

List of source URLs referenced in the answer.

created
Type: integer

Unix timestamp of when the completion was created.

id
Type: string

Unique identifier for the completion.

model
Type: string

The model used for the completion.

object
Type: string
search_results
Type: array object[]

Detailed search results with titles, snippets, and URLs.

date
Type: string
snippet
Type: string
source
Type: string
title
Type: string
url
Type: string
usage
Type: object
completion_tokens
Type: integer

Integer numbers.

prompt_tokens
Type: integer

Integer numbers.

search_context_size
Type: string
total_tokens
Type: integer

Integer numbers.
application/json
400

The request could not be processed. Check the request parameters.
401

A valid Felo API key is required.
402

The request cannot proceed because a billing requirement is not met.
403

The account is not permitted to perform this operation.
429

A request or spending limit has been reached.
502

The service could not complete the request.
503

The API or billing service is temporarily unavailable.
504

The service timed out while processing the request.
default

The operation failed. Keep the response request ID when contacting Felo support.

post/v1/beta/perplexity/sonar-deep-research

curl --request POST https://openapi.felo.ai/v1/beta/perplexity/sonar-deep-research \
  --header "Authorization: Bearer ${FELO_API_KEY:?Set FELO_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model": "sonar-deep-research", "messages": [{"role": "user", "content": "Research HTTP caching strategies for public APIs, with references to standards."}], "max_tokens": 4096, "stream": false}'

Show Schema

{
  "id": "example-sonar-deep-research-completion",
  "model": "sonar-deep-research",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Public API caching combines freshness controls and conditional requests. [1][2]"
      },
      "finish_reason": "stop"
    }
  ],
  "citations": [
    "https://www.rfc-editor.org/rfc/rfc9111.html",
    "https://www.rfc-editor.org/rfc/rfc9110.html"
  ],
  "search_results": [
    {
      "title": "HTTP Caching",
      "url": "https://www.rfc-editor.org/rfc/rfc9111.html"
    },
    {
      "title": "HTTP Semantics",
      "url": "https://www.rfc-editor.org/rfc/rfc9110.html"
    }
  ],
  "usage": {
    "prompt_tokens": 40,
    "completion_tokens": 80,
    "total_tokens": 120
  }
}

Successful response with AI answer and citations

Perplexity Sonar Deep Research

AuthenticationRequired

Perplexity API

Perplexity Sonar Deep Research