Skip to main content

PeakPrivacy API

Use our Chat Completion API to create anonymized requests to LLM

K
Written by Katja Gersdorf
Updated over 2 weeks ago

Create Chat Completions

https://api.peakprivacy.ch/v1/ai/completions

HEADERS

Key

Value

Api-token

api_token from
​https://app.peakprivacy.ch/api-tokens

X-Requested-With

XMLHttpRequest

Accept

application/json

REQUEST BODY SCHEMA: application/json

Key

Value

model

string

ID of the model to use.

Supported models :

- gpt-4-1106-preview
- gpt-4
- gpt-3.5-turbo-1106
- mistral-tiny
- mistral-small
- mistral-medium
- mistral-swiss

messages

Array of objects

The prompt(s) to generate completions for, encoded as a list of dict with role and content. The first prompt role should be user or system.

temperature

number or null [ 0 .. 1 ]
​Default: 0.7
What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

top_p

number or null [ 0 .. 1 ]
​Default: 1
Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

max_tokens

integer or null >= 0
​Default: null
The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. We generally recommend altering this or temperature but not both.

random_seed

integer or null
​Default: null
The seed to use for random sampling. If set, different calls will generate deterministic results.

safe_prompt

boolean or null
​Default: false
Whether to inject a safety prompt before all conversations.

anonymize

boolean or null
​Default: true
Whether to use anonymization for the prompt. Might slightly increase response time due to anonymization & deanonymization algorithms work.

stream

boolean or null
​Default: false
Whether to receive response as a stream or a single object. NOTE: anonymize=true will force stream to be set to false automatically.

messages SCHEMA:

Key

Value

role

string
​system user assistant
Specifies the role of the messages author

content

string
Message(-s) of the conversation with AI

BODY raw

{
    "model": "gpt-4-1106-preview",
    "messages": [
        {
            "role": "assistant",
            "content": "content"
        }
    ],
    "temperature": null,
    "top_p": null,
    "max_tokens": null,
    "random_seed": null,
    "safe_prompt": null,
    "anonymize": true
}

Example request

curl --location --request POST 'https://api.peakprivacy.ch/v1/ai/completions' \
--header 'Api-token: api_token' \
--header 'X-Requested-With: XMLHttpRequest' \
--header 'Accept: application/json' \
--header 'Content-Type: application/json' \
--data-raw '{
	"model": "gpt-4-1106-preview",
    "messages": [
        {
            "role": "user",
            "content": "content"
        }
    ],
    "temperature": null,
    "top_p": null,
    "max_tokens": null,
    "random_seed": null,
    "safe_prompt": null,
    "anonymize": true
}'

Possible Responses

200 - Success

{
    "id": "1df8f5af-c96d-42ba-938a-3f5c4f62e633",
    "object": "chat.completion",
    "created": 1705942239,
    "model": "gpt-3.5-turbo-1106",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "Hello! How can I assist you today?",
                "role": "assistant"
            }
        }
    ],
    "usage": {
        "completion_tokens": 9,
        "prompt_tokens": 8,
        "total_tokens": 17
    }
}

RESPONSE SCHEMA: application/json

Key

Value

id

string

object

string

created

integer

model

string

choices

Array of objects

usage

object

choices SCHEMA: application/json

Key

Value

finish_reason

string

index

string

message

object

message SCHEMA: application/json

Key

Value

role

string

content

string

usage SCHEMA: application/json

Key

Value

completion_tokens

integer

prompt_tokens

integer

total_tokens

integer

400 - Bad Request; Validation Error

{
    "message": "Validation error",
    "errors": {
        "model": [
            "The model field is required."
        ]
    }
}

401 - Unauthenticated; Form Token Expired

{
    "error": "Unauthenticated"
}

403 - Forbidden; Subscription amount limit has been reached

{
    "error": "Subscription amount limit has been reached"
}

response SCHEMA: application/json

Key

Value

error

string

Get supported models list

https://api.peakprivacy.ch/v1/ai/models

HEADERS

Key

Value

Api-token

api_token from

https://app.peakprivacy.ch/api-tokens

X-Requested-With

XMLHttpRequest

Accept

application/json

Example request

curl --location --request GET 'https://api.peakprivacy.ch/v1/ai/models' \
--header 'Api-token: ' \
--header 'X-Requested-With: XMLHttpRequest' \
--header 'Accept: application/json' \
--header 'Content-Type: application/json' \

Response samples

200 - Success

{
    "object": "list",
    "data": [
        {
            "id": "gpt-4-1106-preview",
            "object": "model",
            "created": 0,
            "owned_by": "OpenAI"
        },
        ...
    ]
}

RESPONSE SCHEMA: application/json

Key

Value

object

string

data

Array of objects

data SCHEMA: application/json

Key

Value

id

string

object

string

created

integer

owned_by

object

401 - Unauthenticated; Form Token Expired

{
    "error": "Unauthenticated"
}

response SCHEMA: application/json

Key

Value

error

string



​

Related Articles
Getting started with PeakPrivacy
PeakPrivacy Assistants API
PeakPrivacy Files API
Large Language Models / EndPoints
Prices LLM usage as you go
Did this answer your question?