> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/openlit/openlit/llms.txt
> Use this file to discover all available pages before exploring further.

# API reference

> Authenticate and call the OpenLIT REST API to retrieve prompts and secrets programmatically

The OpenLIT REST API lets you integrate Prompt Hub and Vault directly into any application or script — without installing an SDK. All endpoints accept JSON request bodies and return JSON responses.

## Authentication

Every request must include your OpenLIT API key in the `Authorization` header:

```http theme={null}
Authorization: Bearer <api-key>
```

To create an API key, navigate to **API Keys** in OpenLIT and click **Create API Key**.

## Base URL

Replace the base URL below with the address of your OpenLIT instance:

```
http://127.0.0.1:3000
```

If OpenLIT is deployed on a remote host, substitute the appropriate hostname or IP address.

## Endpoints

### POST /api/prompt/get-compiled

Fetch a prompt from Prompt Hub and optionally compile it with runtime variables.

<CodeGroup>
  ```bash curl theme={null}
  curl --request POST \
    --url http://127.0.0.1:3000/api/prompt/get-compiled \
    --header 'Authorization: Bearer _OPENLIT_API_KEY' \
    --header 'Content-Type: application/json' \
    --data '{
      "name": "prompt_name",
      "shouldCompile": true,
      "variables": { "name": "John" }
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "http://127.0.0.1:3000/api/prompt/get-compiled",
      headers={
          "Authorization": "Bearer _OPENLIT_API_KEY",
          "Content-Type": "application/json",
      },
      json={
          "name": "prompt_name",
          "shouldCompile": True,
          "variables": {"name": "John"},
      },
  )

  print(response.json())
  ```
</CodeGroup>

#### Request parameters

<ParamField path="header.Authorization" type="string" required>
  `Bearer <api-key>` — your OpenLIT API key.
</ParamField>

<ParamField path="body.name" type="string">
  Name of the prompt to retrieve. Use either `name` or `promptId`.
</ParamField>

<ParamField path="body.promptId" type="string">
  Unique ID of the prompt. Use either `promptId` or `name`.
</ParamField>

<ParamField path="body.version" type="string">
  Specific semantic version to retrieve (e.g. `3.2.1`). Omit to get the latest version.
</ParamField>

<ParamField path="body.shouldCompile" type="boolean">
  When `true`, replaces `{{variableName}}` placeholders in the prompt with values from `variables`.
</ParamField>

<ParamField path="body.variables" type="object">
  Key-value pairs substituted into the prompt when `shouldCompile` is `true`.
</ParamField>

<ParamField path="body.metaProperties" type="object">
  Additional metadata stored in the prompt's access history.
</ParamField>

#### Response

```json 200 theme={null}
{
  "err": null,
  "res": {
    "promptId": "88c4cbcd-87f9-4957-a37b-b41066e17471",
    "name": "prompt_name",
    "version": "3.3.3",
    "tags": ["user", "greeting"],
    "metaProperties": { "model": "gpt4" },
    "prompt": "Hello {{name}}, how are you today?",
    "compiledPrompt": "Hello John, how are you today?"
  }
}
```

<ResponseField name="err" type="null | string">
  `null` on success, or an error message string on failure.
</ResponseField>

<ResponseField name="res" type="object">
  <Expandable title="properties" defaultOpen>
    <ResponseField name="promptId" type="string">
      Unique identifier for the prompt.
    </ResponseField>

    <ResponseField name="name" type="string">
      The prompt name as stored in Prompt Hub.
    </ResponseField>

    <ResponseField name="version" type="string">
      Semantic version of the returned prompt (e.g. `3.3.3`).
    </ResponseField>

    <ResponseField name="tags" type="string[]">
      Tags associated with the prompt.
    </ResponseField>

    <ResponseField name="metaProperties" type="object">
      Key-value metadata stored alongside the prompt.
    </ResponseField>

    <ResponseField name="prompt" type="string">
      The raw prompt text, including any unresolved `{{variable}}` placeholders.
    </ResponseField>

    <ResponseField name="compiledPrompt" type="string">
      The prompt with all variables substituted. Present only when `shouldCompile` is `true`.
    </ResponseField>
  </Expandable>
</ResponseField>

***

### POST /api/vault/get-secrets

Retrieve secrets from Vault. Optionally filter by key or tag.

<CodeGroup>
  ```bash curl theme={null}
  curl --request POST \
    --url http://127.0.0.1:3000/api/vault/get-secrets \
    --header 'Authorization: Bearer _OPENLIT_API_KEY' \
    --header 'Content-Type: application/json' \
    --data '{}'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "http://127.0.0.1:3000/api/vault/get-secrets",
      headers={
          "Authorization": "Bearer _OPENLIT_API_KEY",
          "Content-Type": "application/json",
      },
      json={},
  )

  print(response.json())
  ```
</CodeGroup>

#### Request parameters

<ParamField path="header.Authorization" type="string" required>
  `Bearer <api-key>` — your OpenLIT API key.
</ParamField>

<ParamField path="body.key" type="string">
  Fetch a single secret by its key (e.g. `OPENAI_API_KEY`). Omit to fetch all secrets.
</ParamField>

<ParamField path="body.tags" type="string[]">
  Fetch only secrets that have all of the specified tags assigned.
</ParamField>

#### Response

```json 200 theme={null}
{
  "err": null,
  "res": {
    "ANTHROPIC_API_KEY": "ANTHROPIC_API_VALUE",
    "OPENAI_API_KEY": "OPENAI_API_VALUE"
  }
}
```

<ResponseField name="err" type="null | string">
  `null` on success, or an error message string on failure.
</ResponseField>

<ResponseField name="res" type="object">
  A flat object where each key is the secret's key name and each value is the secret's value.
</ResponseField>

***

<CardGroup cols={2}>
  <Card title="Prompt Hub" href="/openlit/prompts/prompt-hub" icon="message">
    Manage and version prompts in the OpenLIT UI
  </Card>

  <Card title="Vault" href="/openlit/secrets/vault" icon="vault">
    Store and manage LLM API keys and secrets centrally
  </Card>
</CardGroup>