Public AI Gateway - Developer Portal

My Zuplo API

Endpointhttps://api.publicai.co

Lists the currently available models

GET

https://api.publicai.co

/v1/models

Returns a list of all available models that can be used with the chat completions endpoint.

Lists the currently available models › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

User-Agent

string · required

User-Agent header identifying the client application

Lists the currently available models › Responses

200

object

string · enum · required

The object type, which is always 'list'

Enum values:

list

object[] · required

The list of models

GET/v1/models

curl --request GET \
  --url https://api.publicai.co/v1/models \
  --header 'Authorization: <string>' \
  --header 'User-Agent: <string>'

shell

Example Responses

{
  "object": "list",
  "data": [
    {
      "id": "swiss-ai/apertus-8b-instruct",
      "object": "model",
      "created": 1677610602,
      "owned_by": "openai"
    }
  ]
}

json

application/json

Creates a model response for the given chat conversation

POST

https://api.publicai.co

/v1/chat/completions

Creates a completion for the chat message

Creates a model response for the given chat conversation › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

User-Agent

string · required

User-Agent header identifying the client application

Creates a model response for the given chat conversation › Request Body

model

string · required

ID of the model to use

object[] · required

A list of messages comprising the conversation so far

temperature

number · min: 0 · max: 2

What sampling temperature to use, between 0 and 2

top_p

number · min: 0 · max: 1

An alternative to sampling with temperature

n

integer · min: 1

How many chat completion choices to generate for each input message

stream

boolean

If set, partial message deltas will be sent

Up to 4 sequences where the API will stop generating further tokens

max_tokens

integer

The maximum number of tokens to generate in the chat completion

presence_penalty

number · min: -2 · max: 2

Number between -2.0 and 2.0

frequency_penalty

number · min: -2 · max: 2

Number between -2.0 and 2.0

logit_bias

object

Modify the likelihood of specified tokens appearing in the completion

user

string

A unique identifier representing your end-user

object[]

Creates a model response for the given chat conversation › Responses

id

string · required

A unique identifier for the chat completion

object

string · enum · required

The object type, which is always 'chat.completion'

Enum values:

chat.completion

created

integer · required

The Unix timestamp (in seconds) of when the chat completion was created

model

string · required

The model used for the chat completion

object[] · required

A list of chat completion choices

object · required

system_fingerprint

string

This fingerprint represents the backend configuration that the model runs with

POST/v1/chat/completions

curl --request POST \
  --url https://api.publicai.co/v1/chat/completions \
  --header 'Authorization: <string>' \
  --header 'Content-Type: application/json' \
  --header 'User-Agent: <string>' \
  --data '
{
  "model": "swiss-ai/apertus-8b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}
'

shell

Example Request Body

{
  "model": "swiss-ai/apertus-8b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}

json

Example Responses

{
  "id": "chatcmpl-6d5e4c0fba54aec4b099fc524c13247a",
  "object": "chat.completion",
  "created": 1757652946,
  "model": "swiss-ai/Apertus-8B-Instruct-2509",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm Apertus, your AI assistant. How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 63,
    "completion_tokens": 19,
    "total_tokens": 82
  }
}

json

application/json

Lists the currently available models

GET

https://api.publicai.co

/v1/models

Returns a list of all available models that can be used with the chat completions endpoint.

Lists the currently available models › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

User-Agent

string · required

User-Agent header identifying the client application

Lists the currently available models › Responses

200

object

string · enum · required

The object type, which is always 'list'

Enum values:

list

object[] · required

The list of models

Creates a model response for the given chat conversation

POST

https://api.publicai.co

/v1/chat/completions

Creates a completion for the chat message

Creates a model response for the given chat conversation › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

User-Agent

string · required

User-Agent header identifying the client application

Creates a model response for the given chat conversation › Request Body

model

string · required

ID of the model to use

object[] · required

A list of messages comprising the conversation so far

temperature

number · min: 0 · max: 2

What sampling temperature to use, between 0 and 2

top_p

number · min: 0 · max: 1

An alternative to sampling with temperature

n

integer · min: 1

How many chat completion choices to generate for each input message

stream

boolean

If set, partial message deltas will be sent

Up to 4 sequences where the API will stop generating further tokens

max_tokens

integer

The maximum number of tokens to generate in the chat completion

presence_penalty

number · min: -2 · max: 2

Number between -2.0 and 2.0

frequency_penalty

number · min: -2 · max: 2

Number between -2.0 and 2.0

logit_bias

object

Modify the likelihood of specified tokens appearing in the completion

user

string

A unique identifier representing your end-user

object[]

Creates a model response for the given chat conversation › Responses

id

string · required

A unique identifier for the chat completion

object

string · enum · required

The object type, which is always 'chat.completion'

Enum values:

chat.completion

created

integer · required

The Unix timestamp (in seconds) of when the chat completion was created

model

string · required

The model used for the chat completion

object[] · required

A list of chat completion choices

object · required

system_fingerprint

string

This fingerprint represents the backend configuration that the model runs with

curl --request POST \ --url https://api.publicai.co/v1/chat/completions \ --header 'Authorization: <string>' \ --header 'Content-Type: application/json' \ --header 'User-Agent: <string>' \ --data ' { "model": "swiss-ai/apertus-8b-instruct", "messages": [ { "role": "user", "content": "Hello!" } ] } '

{ "id": "chatcmpl-6d5e4c0fba54aec4b099fc524c13247a", "object": "chat.completion", "created": 1757652946, "model": "swiss-ai/Apertus-8B-Instruct-2509", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Hello! I'm Apertus, your AI assistant. How can I assist you today?" }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 63, "completion_tokens": 19, "total_tokens": 82 } }