POST
/
chat
/
completions
curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "sonar",
  "messages": [
    {
      "role": "system",
      "content": "Be precise and concise."
    },
    {
      "role": "user",
      "content": "How many stars are there in our galaxy?"
    }
  ]
}'
"<any>"

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
string
required

The name of the model that will complete your prompt. Refer to Supported Models to find all the models offered.

Example:

"sonar"

​
messages
object[]
required

A list of messages comprising the conversation so far.

Example:
[
  {
    "role": "system",
    "content": "Be precise and concise."
  },
  {
    "role": "user",
    "content": "How many stars are there in our galaxy?"
  }
]
​
max_tokens
integer

The maximum number of completion tokens returned by the API. Controls the length of the model's response. If the response would exceed this limit, it will be truncated. Higher values allow for longer responses but may increase processing time and costs.

​
temperature
number
default:0.2

The amount of randomness in the response, valued between 0 and 2. Lower values (e.g., 0.1) make the output more focused, deterministic, and less creative. Higher values (e.g., 1.5) make the output more random and creative. Use lower values for factual/information retrieval tasks and higher values for creative applications.

Required range: 0 <= x < 2
​
top_p
number
default:0.9

The nucleus sampling threshold, valued between 0 and 1. Controls the diversity of generated text by considering only the tokens whose cumulative probability exceeds the top_p value. Lower values (e.g., 0.5) make the output more focused and deterministic, while higher values (e.g., 0.95) allow for more diverse outputs. Often used as an alternative to temperature.

​
search_domain_filter
any[]

A list of domains to limit search results to. Currently limited to 10 domains for Allowlisting and Denylisting. For Denylisting, add a - at the beginning of the domain string. More information about this here.

​
return_images
boolean
default:false

Determines whether search results should include images.

​
return_related_questions
boolean
default:false

Determines whether related questions should be returned.

​
search_recency_filter
string

Filters search results based on time (e.g., 'week', 'day').

​
top_k
number
default:0

The number of tokens to keep for top-k filtering. Limits the model to consider only the k most likely next tokens at each step. Lower values (e.g., 10) make the output more focused and deterministic, while higher values allow for more diverse outputs. A value of 0 disables this filter. Often used in conjunction with top_p to control output randomness.

​
stream
boolean
default:false

Determines whether to stream the response incrementally.

​
presence_penalty
number
default:0

Positive values increase the likelihood of discussing new topics. Applies a penalty to tokens that have already appeared in the text, encouraging the model to talk about new concepts. Values typically range from 0 (no penalty) to 2.0 (strong penalty). Higher values reduce repetition but may lead to more off-topic text.

​
frequency_penalty
number
default:1

Decreases likelihood of repetition based on prior frequency. Applies a penalty to tokens based on how frequently they've appeared in the text so far. Values typically range from 0 (no penalty) to 2.0 (strong penalty). Higher values (e.g., 1.5) reduce repetition of the same words and phrases. Useful for preventing the model from getting stuck in loops.

​
response_format
object

Enables structured JSON output formatting.

​
web_search_options
object

Configuration for using web search in model responses.

Example:
{ "search_context_size": "high" }

Response

200
application/json
OK

The response is of type any.