Orq.ai Documentation - AI Gateway & LLM Collaboration Platform

Retrieve a prompt

curl --request GET \
  --url https://api.orq.ai/v2/prompts/{id} \
  --header 'Authorization: Bearer <token>'

{
  "_id": "<string>",
  "type": "prompt",
  "owner": "<string>",
  "domain_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "created": "<string>",
  "updated": "<string>",
  "display_name": "<string>",
  "prompt_config": {
    "messages": [
      {
        "role": "system",
        "content": "<string>",
        "tool_calls": [
          {
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            },
            "id": "<string>",
            "index": 123
          }
        ],
        "tool_call_id": "<string>"
      }
    ],
    "stream": true,
    "model": "<string>",
    "model_db_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "model_type": "chat",
    "model_parameters": {
      "temperature": 123,
      "maxTokens": 123,
      "topK": 123,
      "topP": 123,
      "frequencyPenalty": 123,
      "presencePenalty": 123,
      "numImages": 123,
      "seed": 123,
      "format": "url",
      "dimensions": "<string>",
      "quality": "<string>",
      "style": "<string>",
      "responseFormat": {
        "type": "json_schema",
        "json_schema": {
          "name": "<string>",
          "schema": {},
          "description": "<string>",
          "strict": true
        },
        "display_name": "<string>"
      },
      "photoRealVersion": "v1",
      "encoding_format": "float",
      "reasoningEffort": "none",
      "budgetTokens": 123,
      "verbosity": "low",
      "thinkingLevel": "low"
    },
    "provider": "openai",
    "integration_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "version": "<string>"
  },
  "created_by_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "updated_by_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "description": "<string>",
  "metadata": {
    "language": "English"
  }
}

GET

/

v2

/

prompts

/

{id}

Retrieve a prompt

curl --request GET \
  --url https://api.orq.ai/v2/prompts/{id} \
  --header 'Authorization: Bearer <token>'

{
  "_id": "<string>",
  "type": "prompt",
  "owner": "<string>",
  "domain_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "created": "<string>",
  "updated": "<string>",
  "display_name": "<string>",
  "prompt_config": {
    "messages": [
      {
        "role": "system",
        "content": "<string>",
        "tool_calls": [
          {
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            },
            "id": "<string>",
            "index": 123
          }
        ],
        "tool_call_id": "<string>"
      }
    ],
    "stream": true,
    "model": "<string>",
    "model_db_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "model_type": "chat",
    "model_parameters": {
      "temperature": 123,
      "maxTokens": 123,
      "topK": 123,
      "topP": 123,
      "frequencyPenalty": 123,
      "presencePenalty": 123,
      "numImages": 123,
      "seed": 123,
      "format": "url",
      "dimensions": "<string>",
      "quality": "<string>",
      "style": "<string>",
      "responseFormat": {
        "type": "json_schema",
        "json_schema": {
          "name": "<string>",
          "schema": {},
          "description": "<string>",
          "strict": true
        },
        "display_name": "<string>"
      },
      "photoRealVersion": "v1",
      "encoding_format": "float",
      "reasoningEffort": "none",
      "budgetTokens": 123,
      "verbosity": "low",
      "thinkingLevel": "low"
    },
    "provider": "openai",
    "integration_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "version": "<string>"
  },
  "created_by_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "updated_by_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "description": "<string>",
  "metadata": {
    "language": "English"
  }
}

Authorizations

Authorization

string

header

required

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

Path Parameters

id

string

required

Unique identifier of the prompt

Response

200 - application/json

Prompt retrieved.

A prompt entity with configuration, metadata, and versioning.

_id

string

required

type

enum<string>

required

Available options:

prompt

owner

string

required

domain_id

string<uuid>

required

created

string

required

updated

string

required

display_name

string

required

The prompt’s name, meant to be displayable in the UI.

Maximum string length: 128

prompt_config

object

required

A list of messages compatible with the openAI schema

Show child attributes

prompt_config.messages

object[]

required

Show child attributes

prompt_config.messages.role

enum<string>

required

The role of the prompt message

Available options:

system,

assistant,

user,

exception,

tool,

prompt,

correction,

expected_output

prompt_config.messages.content

required

The contents of the user message. Either the text content of the message or an array of content parts with a defined type, each can be of type text or image_url when passing in images. You can pass multiple images by adding multiple image_url content parts. Can be null for tool messages in certain scenarios.

prompt_config.messages.tool_calls

object[]

Show child attributes

prompt_config.messages.tool_calls.type

enum<string>

required

Available options:

function

prompt_config.messages.tool_calls.function

object

required

Show child attributes

prompt_config.messages.tool_calls.function.name

string

required

prompt_config.messages.tool_calls.function.arguments

string

required

JSON string arguments for the functions

prompt_config.messages.tool_calls.id

string

prompt_config.messages.tool_calls.index

number

prompt_config.messages.tool_call_id

string | null

prompt_config.stream

boolean

prompt_config.model

string

prompt_config.model_db_id

string<uuid> | null

The id of the resource

prompt_config.model_type

enum<string> | null

The modality of the model

Available options:

chat,

completion,

embedding,

image,

tts,

stt,

rerank,

moderation,

vision

prompt_config.model_parameters

object

Model Parameters: Not all parameters apply to every model

Show child attributes

prompt_config.model_parameters.temperature

number

Only supported on chat and completion models.

prompt_config.model_parameters.maxTokens

number

Only supported on chat and completion models.

prompt_config.model_parameters.topK

number

Only supported on chat and completion models.

prompt_config.model_parameters.topP

number

Only supported on chat and completion models.

prompt_config.model_parameters.frequencyPenalty

number

Only supported on chat and completion models.

prompt_config.model_parameters.presencePenalty

number

Only supported on chat and completion models.

prompt_config.model_parameters.numImages

number

Only supported on image models.

prompt_config.model_parameters.seed

number

Best effort deterministic seed for the model. Currently only OpenAI models support these

prompt_config.model_parameters.format

enum<string>

Only supported on image models.

Available options:

url,

b64_json,

text,

json_object

prompt_config.model_parameters.dimensions

string

Only supported on image models.

prompt_config.model_parameters.quality

string

Only supported on image models.

prompt_config.model_parameters.style

string

Only supported on image models.

prompt_config.model_parameters.responseFormat

An object specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema

Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

Show child attributes

prompt_config.model_parameters.responseFormat.type

enum<string>

required

Available options:

json_schema

prompt_config.model_parameters.responseFormat.json_schema

object

required

Show child attributes

prompt_config.model_parameters.responseFormat.json_schema.name

string

required

prompt_config.model_parameters.responseFormat.json_schema.schema

object

required

Show child attributes

prompt_config.model_parameters.responseFormat.json_schema.schema.{key}

any

prompt_config.model_parameters.responseFormat.json_schema.description

string

prompt_config.model_parameters.responseFormat.json_schema.strict

boolean

prompt_config.model_parameters.responseFormat.display_name

string

prompt_config.model_parameters.photoRealVersion

enum<string>

The version of photoReal to use. Must be v1 or v2. Only available for leonardoai provider

Available options:

v1,

v2

prompt_config.model_parameters.encoding_format

enum<string>

The format to return the embeddings

Available options:

float,

base64

prompt_config.model_parameters.reasoningEffort

enum<string>

Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Available options:

none,

disable,

minimal,

low,

medium,

high

prompt_config.model_parameters.budgetTokens

number

Gives the model enhanced reasoning capabilities for complex tasks. A value of 0 disables thinking. The minimum budget tokens for thinking are 1024. The Budget Tokens should never exceed the Max Tokens parameter. Only supported by Anthropic

prompt_config.model_parameters.verbosity

enum<string>

Controls the verbosity of the model output.

Available options:

low,

medium,

high

prompt_config.model_parameters.thinkingLevel

enum<string>

The level of thinking to use for the model. Only supported by Google AI

Available options:

low,

high

prompt_config.provider

enum<string>

Available options:

openai,

groq,

cohere,

azure,

aws,

google,

google-ai,

huggingface,

togetherai,

perplexity,

anthropic,

leonardoai,

fal,

nvidia,

jina,

elevenlabs,

litellm,

cerebras,

openailike,

bytedance,

mistral,

deepseek,

contextualai,

moonshotai

prompt_config.integration_id

The ID of the integration to use

prompt_config.version

string

created_by_id

string<uuid> | null

updated_by_id

string<uuid> | null

description

string | null

The prompt’s description, meant to be displayable in the UI. Use this field to optionally store a long form explanation of the prompt for your own purpose

metadata

object

Show child attributes

metadata.use_cases

enum<string>[]

A list of use cases that the prompt is meant to be used for. Use this field to categorize the prompt for your own purpose

Available options:

Agents simulations,

Agents,

API interaction,

Autonomous Agents,

Chatbots,

Classification,

Code understanding,

Code writing,

Conversation,

Documents QA,

Evaluation,

Extraction,

Multi-modal,

Self-checking,

Sentiment analysis,

SQL,

Summarization,

Tagging,

Translation (document),

Translation (sentences)

metadata.language

enum<string> | null

The language that the prompt is written in. Use this field to categorize the prompt for your own purpose

Available options:

Chinese,

Dutch,

English,

French,

German,

Russian,

Spanish

Create a prompt

Delete a prompt

⌘I