GET

/v1/schemas/perplexity/chat/v1/sonar?kind=output

Accept:

kind outputactivity chathash a6de4b6d…extracted Oct 3, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `1a269d5596e506d3189e57c3ae84874a21c3532afe8c95de6f21e55f17001f15` { "fetchedAt": 1791005478, "extractorVersion": "1", "verifiedAt": null }

Response body

10 properties · 4 required · 14 $defs

property	type	description	constraints
id*	string	Unique identifier for the completion
model*	string	Model used for generation
created*	integer	Unix timestamp when the completion was created
choices*	Choice[]	Array of completion choices
usage	UsageInfo	Token usage and cost information for a request	nullable
object	string	Object type identifier	default: "chat.completion"
citations	string[]	URLs of sources used to generate the response	nullable
search_results	ApiPublicSearchResult[]	Search results used for context in the response	nullable
images	ImageResult[]	Array of images returned when return_images is true	nullable
related_questions	string[]	Array of related questions returned when return_related_questions is true	nullable

Types

14 $defs

ApiPublicSearchResultobject

A single search result from the web

title*	string	Title of the search result page
url*	string	URL of the search result page
date	string	Publication date of the result	nullable
last_updated	string	Date the result was last updated	nullable
snippet	string	Text snippet from the search result	default: ""
source	enum	Source type of the result (web or attachment)	web \| attachment · default: "web"

ChatMessage-Outputobject

role*	enum	Chat roles enum	system \| user \| assistant \| tool
content*	string \| ChatMessageContentTextChunk \| ChatMessageContentImageChunk \| ChatMessageContentFileChunk[]		nullable

ChatMessageContentFileChunkobject

type*	const	"file_url"
file_url*	URL \| string
file_name	string	nullable

ChatMessageContentImageChunkobject

type*	const		"image_url"
image_url*	URL \| string

ChatMessageContentPDFChunkobject

type*	const		"pdf_url"
pdf_url*	URL \| string

ChatMessageContentTextChunkobject

type*	const		"text"
text*	string

ChatMessageContentVideoChunkobject

type*	const		"video_url"
video_url*	VideoURL \| string

ChatMessageRoleenum

Chat roles enum

system | user | assistant | tool

Choiceobject

A single completion choice

index*	integer	Index of the choice in the array
finish_reason	enum	Reason generation stopped (stop or length)	stop \| length · nullable
message*	ChatMessage-Output	Complete message (non-streaming)
delta*	ChatMessage-Output	Incremental message delta (streaming)

Costobject

Cost breakdown for a chat completion request

input_tokens_cost*	number	Cost for input tokens in USD
output_tokens_cost*	number	Cost for output tokens in USD
reasoning_tokens_cost	number	Cost for reasoning tokens in USD	nullable
request_cost	number	Cost for web search requests in USD (includes pro search cost if applicable)	nullable
citation_tokens_cost	number	Cost for citation tokens in USD	nullable
search_queries_cost	number	Cost for search queries in USD	nullable
total_cost*	number	Total cost for the request in USD

ImageResultobject

A single image search result

image_url*	string	URL of the image
origin_url*	string	Original URL where the image was found
height*	integer	Height of the image in pixels	format: int64
width*	integer	Width of the image in pixels	format: int64
title	string	Title or description of the image

URLobject

url*

string

UsageInfoobject

Token usage and cost information for a request

prompt_tokens*	integer	Number of tokens in the prompt/input
completion_tokens*	integer	Number of tokens in the completion/output
total_tokens*	integer	Total tokens used (prompt + completion)
search_context_size	string	Size of search context used	nullable
citation_tokens	integer	Number of tokens used for citations	nullable
num_search_queries	integer	Number of search queries executed	nullable
reasoning_tokens	integer	Number of tokens used for reasoning	nullable
cost*	Cost	Cost breakdown for the request

VideoURLobject

url*	string
frame_interval	string \| integer		default: 25

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"perplexity","endpointId":"v1/sonar","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}