OpenAI Compatible

Chat Completions

post

OpenAI Compatible API Endpoint for Foresight Models.

Authorizations

HTTPBearer

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

modelstringRequired

ID of the model to use

temperatureany ofOptional

Sampling temperature between 0 and 2

numberOptional

or

nullOptional

max_tokensany ofOptional

Maximum number of tokens to generate

integerOptional

or

nullOptional

top_pany ofOptional

Nucleus sampling parameter

numberOptional

or

nullOptional

streamany ofOptional

Whether to stream back partial progress

Default: false

booleanOptional

or

nullOptional

nany ofOptional

Number of chat completion choices to generate

Default: 1

integerOptional

or

nullOptional

stopany ofOptional

Up to 4 sequences where the API will stop generating

stringOptional

or

string[]Optional

or

nullOptional

seedany ofOptional

Deterministic sampling seed

integerOptional

or

nullOptional

Responses

200

Successful Response

application/json

idstringRequired

A unique identifier for the chat completion

objectconst: chat.completionOptional

The object type

Default: chat.completion

createdintegerRequired

Unix timestamp of when the completion was created

modelstringRequired

The model used for the chat completion

usageany ofOptional

Usage statistics for the completion request

or

nullOptional

422

Validation Error

application/json

post

/openai/chat/completions

HTTPcURLJavaScriptPython

POST /api/public/v1/openai/chat/completions HTTP/1.1
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 217

{
  "messages": [
    {
      "content": "Will Bitcoin increase by more than 10% over the next 3 months? Answer as a probability between 0 and 1 between <answer></answer> tags.",
      "role": "user"
    }
  ],
  "model": "LightningRodLabs/foresight-v3"
}

{
  "id": "text",
  "object": "chat.completion",
  "created": 1,
  "model": "text",
  "choices": [
    {
      "index": 1,
      "message": {
        "role": "text",
        "content": "text"
      },
      "finish_reason": "text"
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1
  }
}

List Models

get

List available models.

Responses

200

Successful Response

application/json

objectconst: listOptional

The object type

Default: list

get

/openai/models

HTTPcURLJavaScriptPython

GET /api/public/v1/openai/models HTTP/1.1
Accept: */*

200

Successful Response

{
  "object": "list",
  "data": [
    {
      "id": "text",
      "object": "model",
      "created": 0,
      "owned_by": "lightningrodlabs",
      "name": "",
      "description": "",
      "context_length": 0,
      "max_completion_tokens": 0,
      "pricing": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      }
    }
  ]
}

Completions

post

OpenAI-compatible text completion endpoint.

Authorizations

HTTPBearer

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

modelstringRequired

ID of the model to use

promptany ofRequired

The prompt(s) to generate completions for

stringOptional

or

string[]Optional

temperatureany ofOptional

Sampling temperature between 0 and 2

numberOptional

or

nullOptional

max_tokensany ofOptional

Maximum number of tokens to generate

integerOptional

or

nullOptional

top_pany ofOptional

Nucleus sampling parameter

numberOptional

or

nullOptional

streamany ofOptional

Whether to stream back partial progress

Default: false

booleanOptional

or

nullOptional

nany ofOptional

Number of completions to generate

Default: 1

integerOptional

or

nullOptional

stopany ofOptional

Up to 4 sequences where the API will stop generating

stringOptional

or

string[]Optional

or

nullOptional

seedany ofOptional

Deterministic sampling seed

integerOptional

or

nullOptional

Responses

200

Successful Response

application/json

idstringRequired

A unique identifier for the completion

objectconst: text_completionOptional

The object type

Default: text_completion

createdintegerRequired

Unix timestamp of when the completion was created

modelstringRequired

The model used for the completion

usageany ofOptional

Usage statistics for the completion request

or

nullOptional

422

Validation Error

application/json

post

/openai/completions

HTTPcURLJavaScriptPython

POST /api/public/v1/openai/completions HTTP/1.1
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 117

{
  "model": "text",
  "prompt": "text",
  "temperature": 1,
  "max_tokens": 1,
  "top_p": 1,
  "stream": false,
  "n": 1,
  "stop": "text",
  "seed": 1
}

{
  "id": "text",
  "object": "text_completion",
  "created": 1,
  "model": "text",
  "choices": [
    {
      "index": 1,
      "text": "text",
      "finish_reason": "text"
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1
  }
}