### Make Example Executable and Run

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Grant execute permissions to a new example script and then run it against your API.

```sh
$ chmod +x examples/<your-example>.py
```

```sh
$ ./examples/<your-example>.py
```

--------------------------------

### Install aiohttp for Async OpenAI Client (Shell)

Source: https://github.com/openai/openai-python/blob/main/README.md

Install 'aiohttp' to enable improved concurrency performance for the AsyncOpenAI client. This command installs the 'openai' package with the 'aiohttp' extra.

```sh
# install from PyPI
pip install openai[aiohttp]
```

--------------------------------

### Install OpenAI Python Library

Source: https://github.com/openai/openai-python/blob/main/README.md

Use pip to install the OpenAI Python client library from PyPI.

```sh
# install from PyPI
pip install openai
```

--------------------------------

### Python Example File Template

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Template for adding a new Python example file in the `examples/` directory, including the shebang for Rye.

```py
# add an example to examples/<your-example>.py

#!/usr/bin/env -S rye run python
…
```

--------------------------------

### Install Development Dependencies with pip

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Install all development dependencies using pip after setting up a virtual environment manually.

```sh
$ pip install -r requirements-dev.lock
```

--------------------------------

### Install Python Package from Wheel File

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Install the built Python package efficiently from its generated wheel file.

```sh
$ pip install ./path-to-wheel-file.whl
```

--------------------------------

### Install openai-python from Git via SSH

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Install the openai-python library directly from the GitHub repository using pip and SSH.

```sh
$ pip install git+ssh://git@github.com/openai/openai-python.git
```

--------------------------------

### get /models

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all available models.

```APIDOC
## GET /models

### Description
Lists all available models.

### Method
GET

### Endpoint
/models

### Parameters
*No parameters.*

### Response
#### Success Response (200)
- **SyncPage[Model]** (array) - A list of model objects.
```

--------------------------------

### Install Bedrock Dependencies for OpenAI Python

Source: https://github.com/openai/openai-python/blob/main/README.md

Install the optional Bedrock dependencies to enable AWS credential chain and SigV4 authentication for the OpenAI Python library.

```sh
pip install 'openai[bedrock]'
```

--------------------------------

### Start Mock Server for Tests

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Run the script to set up a mock server, which is required for most tests.

```sh
$ ./scripts/mock
```

--------------------------------

### AsyncOpenAI().responses.create

Source: https://github.com/openai/openai-python/blob/main/README.md

Demonstrates how to use the asynchronous OpenAI client to create a response, showing the basic setup and an `await` call.

```APIDOC
## AsyncOpenAI().responses.create

### Description
This method allows you to asynchronously create a response from the model. It's part of the `AsyncOpenAI` client, designed for non-blocking operations.

### Method
`client.responses.create`

### Parameters
#### Request Body
- **model** (string) - Required - The ID of the model to use (e.g., "gpt-5.5").
- **input** (string) - Required - The text prompt for the model.

### Request Example
```python
import os
import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key=os.environ.get("OPENAI_API_KEY"),
)


async def main() -> None:
    response = await client.responses.create(
        model="gpt-5.5", input="Explain disestablishmentarianism to a smart five year old."
    )
    print(response.output_text)


asyncio.run(main())
```
```

--------------------------------

### get /fine_tuning/jobs

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists fine-tuning jobs.

```APIDOC
## GET /fine_tuning/jobs

### Description
Lists fine-tuning jobs.

### Method
GET

### Endpoint
/fine_tuning/jobs

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for listing fine-tuning jobs.

### Response
#### Success Response (200)
- **SyncCursorPage[FineTuningJob]** (array) - A list of fine-tuning job objects.
```

--------------------------------

### get /organization/projects

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all projects for the organization, with optional filtering.

```APIDOC
## GET /organization/projects

### Description
Lists all projects for the organization, with optional filtering.

### Method
GET

### Endpoint
/organization/projects

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination.

### Response
#### Success Response (200)
- **SyncConversationCursorPage[Project]** (object) - A paginated list of project objects.
```

--------------------------------

### get /skills

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all available skills, with optional filtering and pagination.

```APIDOC
## GET /skills

### Description
Lists all available skills.

### Method
GET

### Endpoint
/skills

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination.

### Response
#### Success Response (200)
- **SyncCursorPage[Skill]** (object) - A paginated list of skill objects.
```

--------------------------------

### GET /vector_stores

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all available vector stores.

```APIDOC
## GET /vector_stores

### Description
Lists all available vector stores.

### Method
GET

### Endpoint
/vector_stores

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination of the list.

### Response
#### Success Response (200)
- **SyncCursorPage[VectorStore]** (object) - A paginated list of vector store objects.
```

--------------------------------

### GET /videos

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all available video resources, with optional filtering parameters.

```APIDOC
## GET /videos

### Description
Lists all available video resources, with optional filtering parameters.

### Method
GET

### Endpoint
/videos

### Query Parameters
- **params** (object) - Optional - Parameters for listing videos.

### Response
#### Success Response (200)
- **SyncConversationCursorPage[Video]** (object) - A paginated list of video objects.
```

--------------------------------

### Synchronize Rye Environment with All Features

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

After manually installing Rye, use this command to synchronize the project dependencies and enable all features.

```sh
$ rye sync --all-features
```

--------------------------------

### GET /batches

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all batch jobs, with optional filtering and pagination.

```APIDOC
## GET /batches

### Description
Lists all batch jobs, with optional filtering and pagination.

### Method
GET

### Endpoint
/batches

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination of batch jobs.
```

--------------------------------

### get /skills/{skill_id}/versions/{version}/content

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves the binary content for a specific version of a skill.

```APIDOC
## GET /skills/{skill_id}/versions/{version}/content

### Description
Retrieves the content of a specific skill version.

### Method
GET

### Endpoint
/skills/{skill_id}/versions/{version}/content

### Parameters
#### Path Parameters
- **skill_id** (string) - Required - The ID of the skill.
- **version** (string) - Required - The version identifier of the skill.

### Response
#### Success Response (200)
- **HttpxBinaryResponseContent** (binary) - The binary content of the skill version.
```

--------------------------------

### client.beta.threads.runs.steps.list

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all steps for a run in a thread, allowing pagination and filtering.

```APIDOC
## GET /threads/{thread_id}/runs/{run_id}/steps

### Description
Lists all steps for a run in a thread, allowing pagination and filtering.

### Method
GET

### Endpoint
/threads/{thread_id}/runs/{run_id}/steps

### Parameters
#### Path Parameters
- **run_id** (string) - Required - The ID of the run to list steps for.
- **thread_id** (string) - Required - The ID of the thread to which the run belongs.

### Response
#### Success Response (200)
- **SyncCursorPage[RunStep]** (object) - A paginated list of RunStep objects.
```

--------------------------------

### get /skills/{skill_id}/versions

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all versions for a specified skill, with optional filtering and pagination.

```APIDOC
## GET /skills/{skill_id}/versions

### Description
Lists all versions for a specific skill.

### Method
GET

### Endpoint
/skills/{skill_id}/versions

### Parameters
#### Path Parameters
- **skill_id** (string) - Required - The ID of the skill to list versions for.

#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination.

### Response
#### Success Response (200)
- **SyncCursorPage[SkillVersion]** (object) - A paginated list of skill version objects.
```

--------------------------------

### GET /containers

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all containers accessible to the user. This method supports pagination and filtering through optional parameters.

```APIDOC
## GET /containers\n\n### Description\nLists all containers accessible to the user. This method supports pagination and filtering through optional parameters.\n\n### Method\nGET\n\n### Endpoint\n/containers\n\n### Parameters\n#### Query Parameters\n- **params** (object) - Optional - Parameters for listing containers, as defined by `container_list_params.py`.\n\n### Response\n#### Success Response (200)\n- **response** (SyncCursorPage[ContainerListResponse]) - A paginated list of container objects.
```

--------------------------------

### get /evals

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all evaluations, with support for pagination and filtering through optional parameters.

```APIDOC
## GET /evals

### Description
Lists all evaluations, with support for pagination and filtering.

### Method
GET

### Endpoint
/evals

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination. See `eval_list_params.py` for schema details.

### Response
#### Success Response (200)
- **response** (SyncCursorPage[EvalListResponse]) - A paginated list of evaluation objects.
```

--------------------------------

### GET /organization/projects/{project_id}/api_keys

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all API keys associated with a specific project.

```APIDOC
## GET /organization/projects/{project_id}/api_keys

### Description
Lists all API keys associated with a specific project.

### Method
GET

### Endpoint
/organization/projects/{project_id}/api_keys

### Parameters
#### Path Parameters
- **project_id** (string) - Required - The ID of the project.

#### Query Parameters
- **params** (object) - Optional - Additional parameters for filtering and pagination, as defined in `api_key_list_params.py`.

### Response
#### Success Response (200)
- **SyncConversationCursorPage[ProjectAPIKey]** (object) - A paginated list of API keys.

```

--------------------------------

### Check Installed openai-python Version

Source: https://github.com/openai/openai-python/blob/main/README.md

Use this snippet to programmatically determine the version of the openai-python package currently installed and active in your Python environment.

```python
import openai
print(openai.__version__)
```

--------------------------------

### GET /files

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all files uploaded by the organization, with optional filtering parameters.

```APIDOC
## GET /files

### Description
Lists all files uploaded by the organization.

### Method
GET

### Endpoint
/files

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for listing files.

### Response
#### Success Response (200)
- **SyncCursorPage[FileObject]** (object) - A paginated list of file objects.
```

--------------------------------

### List Organization Admin API Keys in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Get a paginated list of all Admin API Keys associated with the organization.

```python
client.admin.organization.admin_api_keys.list(**params)
```

--------------------------------

### Bootstrap Development Environment with Rye

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Run this script to automatically provision a Python environment and manage dependencies using Rye.

```sh
$ ./scripts/bootstrap
```

--------------------------------

### AsyncOpenAI().chat.completions.create (with aiohttp)

Source: https://github.com/openai/openai-python/blob/main/README.md

Demonstrates how to use the asynchronous OpenAI client with `aiohttp` as the HTTP backend to create chat completions.

```APIDOC
## AsyncOpenAI().chat.completions.create (with aiohttp)

### Description
This method allows you to asynchronously create chat completions using the `AsyncOpenAI` client configured with `aiohttp` for improved concurrency performance.

### Method
`client.chat.completions.create`

### Parameters
#### Request Body
- **messages** (array) - Required - A list of message objects comprising the conversation.
    - **role** (string) - Required - The role of the message sender (e.g., "user").
    - **content** (string) - Required - The content of the message.
- **model** (string) - Required - The ID of the model to use (e.g., "gpt-5.5").

### Request Example
```python
import os
import asyncio
from openai import DefaultAioHttpClient
from openai import AsyncOpenAI


async def main() -> None:
    async with AsyncOpenAI(
        api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
        http_client=DefaultAioHttpClient(),
    ) as client:
        chat_completion = await client.chat.completions.create(
            messages=[
                {
                    "role": "user",
                    "content": "Say this is a test",
                }
            ],
            model="gpt-5.5",
        )


asyncio.run(main())
```
```

--------------------------------

### client.beta.threads.create_and_run

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates a new thread and immediately initiates a run on it. This combines the thread creation and run initiation steps into a single call, useful for starting a new assistant interaction directly. It accepts parameters for both thread creation and run configuration.

```APIDOC
## POST /threads/runs

### Description
Creates a new thread and immediately runs it.

### Method
POST

### Endpoint
/threads/runs

### Request Body
- **params** (object) - Required - Parameters for creating and running the thread, including assistant ID and initial messages.

### Response
#### Success Response (200)
- **Run** (object) - The run object initiated for the new thread.
```

--------------------------------

### GET /organization/spend_alerts

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all spend alerts for the organization.

```APIDOC
## GET /organization/spend_alerts

### Description
Lists all spend alerts for the organization.

### Method
GET

### Endpoint
/organization/spend_alerts

### Parameters
#### Query Parameters
- **params** (object) - Optional - Query parameters for filtering and pagination. Refer to `spend_alert_list_params.py` for details.

### Response
#### Success Response (200)
- **SyncConversationCursorPage[OrganizationSpendAlert]** (object) - A paginated list of spend alert objects.
```

--------------------------------

### Configure AsyncOpenAI Client with aiohttp Backend (Python)

Source: https://github.com/openai/openai-python/blob/main/README.md

Use this snippet to instantiate AsyncOpenAI with DefaultAioHttpClient for improved concurrency. Ensure 'aiohttp' is installed before using this configuration.

```python
import os
import asyncio
from openai import DefaultAioHttpClient
from openai import AsyncOpenAI


async def main() -> None:
    async with AsyncOpenAI(
        api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
        http_client=DefaultAioHttpClient(),
    ) as client:
        chat_completion = await client.chat.completions.create(
            messages=[
                {
                    "role": "user",
                    "content": "Say this is a test"
                }
            ],
            model="gpt-5.5"
        )


asyncio.run(main())
```

--------------------------------

### GET /organization/roles

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all roles within the organization.

```APIDOC
## GET /organization/roles

### Description
Lists all roles within the organization.

### Method
GET

### Endpoint
/organization/roles

### Parameters
#### Query Parameters
- **params** (object) - Optional - Query parameters for filtering and pagination. Refer to `role_list_params.py` for details.

### Response
#### Success Response (200)
- **SyncNextCursorPage[Role]** (object) - A paginated list of role objects.
```

--------------------------------

### Execute Project Tests

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Run the project's test suite after ensuring a mock server is set up.

```sh
$ ./scripts/test
```

--------------------------------

### get /organization/costs

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves cost data for an organization.

```APIDOC
## GET /organization/costs

### Description
Retrieves cost data for an organization.

### Method
GET

### Endpoint
/organization/costs

### Parameters
This endpoint accepts various parameters for filtering and pagination, but specific details are not provided in the source.

### Response
#### Success Response (200)
Returns a UsageCostsResponse object containing the requested cost data.
```

--------------------------------

### Initialize Legacy BedrockOpenAI Client with AWS Profile

Source: https://github.com/openai/openai-python/blob/main/README.md

Initialize the legacy `BedrockOpenAI` client, specifying the AWS region and a named profile for authentication.

```py
from openai import BedrockOpenAI

client = BedrockOpenAI(
    aws_region="us-west-2",
    aws_profile="my-profile",
)
```

--------------------------------

### get /fine_tuning/jobs/{fine_tuning_job_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a fine-tuning job.

```APIDOC
## GET /fine_tuning/jobs/{fine_tuning_job_id}

### Description
Retrieves a fine-tuning job.

### Method
GET

### Endpoint
/fine_tuning/jobs/{fine_tuning_job_id}

### Parameters
#### Path Parameters
- **fine_tuning_job_id** (string) - Required - The ID of the fine-tuning job to retrieve.

### Response
#### Success Response (200)
- **FineTuningJob** (object) - The fine-tuning job object.
```

--------------------------------

### Create a Container (Python)

Source: https://github.com/openai/openai-python/blob/main/api.md

Call the `create` method to provision a new container with specified parameters.

```python
client.containers.create(**params) -> ContainerCreateResponse
```

--------------------------------

### Create a Vector Store File Batch

Source: https://github.com/openai/openai-python/blob/main/api.md

Initiate the creation of a new file batch within a specified vector store using the `create` method.

```python
client.vector_stores.file_batches.create(vector_store_id, **params)
```

--------------------------------

### GET /projects/{project_id}/users/{user_id}/roles

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all roles assigned to a user within a project.

```APIDOC
## GET /projects/{project_id}/users/{user_id}/roles

### Description
Lists all roles assigned to a user within a project.

### Method
GET

### Endpoint
/projects/{project_id}/users/{user_id}/roles

### Parameters
#### Path Parameters
- **user_id** (string) - Required - The ID of the user.
- **project_id** (string) - Required - The ID of the project.

#### Query Parameters
- **params** (object) - Optional - Additional parameters for filtering or pagination.

### Response
#### Success Response (200)
- **SyncNextCursorPage[RoleListResponse]** (object) - A paginated list of role assignment responses.

```

--------------------------------

### get /organization/projects/{project_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific project by its ID.

```APIDOC
## GET /organization/projects/{project_id}

### Description
Retrieves a specific project by its ID.

### Method
GET

### Endpoint
/organization/projects/{project_id}

### Parameters
#### Path Parameters
- **project_id** (string) - Required - The ID of the project to retrieve.

### Response
#### Success Response (200)
- **Project** (object) - The retrieved project object.
```

--------------------------------

### Initialize AzureOpenAI Client and Make Chat Completion Request (Python)

Source: https://github.com/openai/openai-python/blob/main/README.md

Initialize the `AzureOpenAI` client with a specific API version and Azure endpoint, then make a chat completion request using a deployment name as the model.

```python
from openai import AzureOpenAI

# gets the API Key from environment variable AZURE_OPENAI_API_KEY
client = AzureOpenAI(
    # https://learn.microsoft.com/azure/ai-services/openai/reference#rest-api-versioning
    api_version="2023-07-01-preview",
    # https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal#create-a-resource
    azure_endpoint="https://example-endpoint.openai.azure.com",
)

completion = client.chat.completions.create(
    model="deployment-name",  # e.g. gpt-35-instant
    messages=[
        {
            "role": "user",
            "content": "How do I output all files in a directory using Python?"
        }
    ]
)
print(completion.to_json())
```

--------------------------------

### GET /assistants

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all Assistants, with options for filtering and pagination. This allows you to retrieve a collection of Assistants managed by your account.

```APIDOC
## GET /assistants

### Description
Lists all Assistants, with options for filtering and pagination.

### Method
GET

### Endpoint
/assistants

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for listing Assistants, such as `limit`, `order`, `after`, or `before` for pagination.
```

--------------------------------

### get /organization/certificates

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all certificates for the organization, with optional filtering.

```APIDOC
## GET /organization/certificates

### Description
Lists all certificates for the organization, with optional filtering.

### Method
GET

### Endpoint
/organization/certificates

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for filtering and pagination.

### Response
#### Success Response (200)
- **SyncConversationCursorPage[CertificateListResponse]** (object) - A paginated list of certificate response objects.
```

--------------------------------

### POST /fine_tuning/alpha/graders/run

Source: https://github.com/openai/openai-python/blob/main/api.md

Runs a fine-tuning alpha grader.

```APIDOC
## POST /fine_tuning/alpha/graders/run

### Description
Runs a fine-tuning alpha grader.

### Method
POST

### Endpoint
/fine_tuning/alpha/graders/run

### Parameters
#### Request Body
- **params** (object) - Required - Parameters for running the grader.

### Response
#### Success Response (200)
- **GraderRunResponse** (object) - The response from running the grader.
```

--------------------------------

### get /organization/certificates/{certificate_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific certificate by its ID.

```APIDOC
## GET /organization/certificates/{certificate_id}

### Description
Retrieves a specific certificate by its ID.

### Method
GET

### Endpoint
/organization/certificates/{certificate_id}

### Parameters
#### Path Parameters
- **certificate_id** (string) - Required - The ID of the certificate to retrieve.

#### Query Parameters
- **params** (object) - Optional - Additional parameters for the request.

### Response
#### Success Response (200)
- **Certificate** (object) - The retrieved certificate object.
```

--------------------------------

### client.responses.create (Vision with image URL)

Source: https://github.com/openai/openai-python/blob/main/README.md

Demonstrates how to use the `client.responses.create` method to process an image from a URL with a text prompt using the Vision model.

```APIDOC
## client.responses.create (Vision with image URL)

### Description
This method allows you to send a text prompt and an image URL to the model for analysis. It's used for Vision capabilities, enabling the model to understand and respond based on image content.

### Method
`client.responses.create`

### Parameters
#### Request Body
- **model** (string) - Required - The ID of the model to use (e.g., "gpt-5.5").
- **input** (array) - Required - A list of message objects.
    - **role** (string) - Required - The role of the message sender, typically "user".
    - **content** (array) - Required - A list of content parts.
        - **type** (string) - Required - The type of content, either "input_text" or "input_image".
        - **text** (string) - Required - (For type "input_text") The text prompt.
        - **image_url** (string) - Required - (For type "input_image") The URL of the image.

### Request Example
```python
prompt = "What is in this image?"
img_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/d5/2023_06_08_Raccoon1.jpg/1599px-2023_06_08_Raccoon1.jpg"

response = client.responses.create(
    model="gpt-5.5",
    input=[
        {
            "role": "user",
            "content": [
                {"type": "input_text", "text": prompt},
                {"type": "input_image", "image_url": f"{img_url}"},
            ],
        }
    ],
)
```
```

--------------------------------

### GET /organization/roles/{role_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific role by its ID.

```APIDOC
## GET /organization/roles/{role_id}

### Description
Retrieves a specific role by its ID.

### Method
GET

### Endpoint
/organization/roles/{role_id}

### Parameters
#### Path Parameters
- **role_id** (string) - Required - The unique identifier of the role to retrieve.

### Response
#### Success Response (200)
- **Role** (object) - The retrieved role object.
```

--------------------------------

### GET /organization/audit_logs

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a list of audit logs for the organization.

```APIDOC
## GET /organization/audit_logs

### Description
Retrieves a list of audit logs for the organization.

### Method
GET

### Endpoint
/organization/audit_logs

### Parameters
#### Query Parameters
- **params** (object) - Optional - Additional query parameters for filtering and pagination.

### Response
#### Success Response (200)
- **data** (array of AuditLogListResponse) - A list of audit log entries.
- **has_next_page** (boolean) - Indicates if there are more pages of results.

#### Response Example
```json
{
  "data": [
    {
      "id": "log_123",
      "event": "user.login",
      "actor": "user_abc",
      "timestamp": 1678886400
    }
  ],
  "has_next_page": false
}
```
```

--------------------------------

### client.responses.create (Vision with base64 image)

Source: https://github.com/openai/openai-python/blob/main/README.md

Demonstrates how to use the `client.responses.create` method to process a base64 encoded image with a text prompt using the Vision model.

```APIDOC
## client.responses.create (Vision with base64 image)

### Description
This method allows you to send a text prompt and a base64 encoded image string to the model for analysis. It's used for Vision capabilities, enabling the model to understand and respond based on image content.

### Method
`client.responses.create`

### Parameters
#### Request Body
- **model** (string) - Required - The ID of the model to use (e.g., "gpt-5.5").
- **input** (array) - Required - A list of message objects.
    - **role** (string) - Required - The role of the message sender, typically "user".
    - **content** (array) - Required - A list of content parts.
        - **type** (string) - Required - The type of content, either "input_text" or "input_image".
        - **text** (string) - Required - (For type "input_text") The text prompt.
        - **image_url** (string) - Required - (For type "input_image") The base64 encoded image string, prefixed with `data:image/<format>;base64,`.

### Request Example
```python
import base64
from openai import OpenAI

client = OpenAI()

prompt = "What is in this image?"
with open("path/to/image.png", "rb") as image_file:
    b64_image = base64.b64encode(image_file.read()).decode("utf-8")

response = client.responses.create(
    model="gpt-5.5",
    input=[
        {
            "role": "user",
            "content": [
                {"type": "input_text", "text": prompt},
                {"type": "input_image", "image_url": f"data:image/png;base64,{b64_image}"},
            ],
        }
    ],
)
```
```

--------------------------------

### Helper Methods for Creating Assistant Streams (Python)

Source: https://github.com/openai/openai-python/blob/main/helpers.md

The SDK provides several helper methods to initiate different types of Assistant runs and stream their responses.

```python
client.beta.threads.runs.stream()
```

```python
client.beta.threads.create_and_run_stream()
```

```python
client.beta.threads.runs.submit_tool_outputs_stream()
```

--------------------------------

### get /models/{model}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves information about a specific model.

```APIDOC
## GET /models/{model}

### Description
Retrieves information about a specific model.

### Method
GET

### Endpoint
/models/{model}

### Parameters
#### Path Parameters
- **model** (string) - Required - The ID of the model to retrieve.

### Response
#### Success Response (200)
- **Model** (object) - The model object containing details about the requested model.
```

--------------------------------

### GET /conversations/{conversation_id}

Source: https://github.com/openai/openai-python/blob/main/src/openai/resources/conversations/api.md

Retrieves a specific conversation by its ID.

```APIDOC
## GET /conversations/{conversation_id}

### Description
Retrieves a specific conversation by its ID.

### Method
GET

### Endpoint
/conversations/{conversation_id}

### Parameters
#### Path Parameters
- **conversation_id** (string) - Required - The ID of the conversation to retrieve.

### Response
#### Success Response (200)
- **Conversation** (object) - The retrieved conversation object.
```

--------------------------------

### Create and Run a Thread in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates a new thread and immediately runs it, returning a Run object.

```python
client.beta.threads.create_and_run(**params) -> Run
```

--------------------------------

### GET /responses/{response_id}

Source: https://github.com/openai/openai-python/blob/main/src/openai/resources/responses/api.md

Retrieves a specific response by its ID.

```APIDOC
## GET /responses/{response_id}\n\n### Description\nRetrieves a specific response by its ID.\n\n### Method\nGET\n\n### Endpoint\n/responses/{response_id}\n\n### Parameters\n#### Path Parameters\n- **response_id** (string) - Required - The ID of the response to retrieve.\n\n#### Query Parameters\n- **params** (object) - Optional - Additional parameters for the request.\n\n### Response\n#### Success Response (200)\n- **Response** (object) - The retrieved Response object.
```

--------------------------------

### Create Assistant in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Use this method to create a new Assistant instance with specified parameters.

```python
client.beta.assistants.create(**params)
```

--------------------------------

### GET /videos/characters/{character_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific character by its unique identifier.

```APIDOC
## GET /videos/characters/{character_id}

### Description
Retrieves a specific character by its unique identifier.

### Method
GET

### Endpoint
/videos/characters/{character_id}

### Parameters
#### Path Parameters
- **character_id** (string) - Required - The unique identifier of the character to retrieve.

### Response
#### Success Response (200)
- **VideoGetCharacterResponse** (object) - The retrieved character response.
```

--------------------------------

### Build Python Package Distribution

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Create distributable `.tar.gz` and `.whl` files for the library using either Rye or the standard Python build module.

```sh
$ rye build
```

```sh
$ python -m build
```

--------------------------------

### Activate Virtual Environment and Run Python Script

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Activate the project's virtual environment, then run a Python script without the `rye run` prefix.

```sh
# Activate the virtual environment - https://docs.python.org/3/library/venv.html#how-venvs-work
$ source .venv/bin/activate
```

```sh
# now you can omit the `rye run` prefix
$ python script.py
```

--------------------------------

### get /skills/{skill_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific skill by its unique identifier.

```APIDOC
## GET /skills/{skill_id}

### Description
Retrieves a specific skill by its ID.

### Method
GET

### Endpoint
/skills/{skill_id}

### Parameters
#### Path Parameters
- **skill_id** (string) - Required - The ID of the skill to retrieve.

### Response
#### Success Response (200)
- **Skill** (object) - The retrieved skill object.
```

--------------------------------

### GET /organization/spend_alerts/{alert_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific spend alert by its ID.

```APIDOC
## GET /organization/spend_alerts/{alert_id}

### Description
Retrieves a specific spend alert by its ID.

### Method
GET

### Endpoint
/organization/spend_alerts/{alert_id}

### Parameters
#### Path Parameters
- **alert_id** (string) - Required - The unique identifier of the spend alert to retrieve.

### Response
#### Success Response (200)
- **OrganizationSpendAlert** (object) - The retrieved spend alert object.
```

--------------------------------

### Create Organization Admin API Key in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Use the create method to generate a new Admin API Key for the organization.

```python
client.admin.organization.admin_api_keys.create(**params)
```

--------------------------------

### POST /videos

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates a new video resource with the provided parameters.

```APIDOC
## POST /videos

### Description
Creates a new video resource with the provided parameters.

### Method
POST

### Endpoint
/videos

### Request Body
- **params** (object) - Required - Parameters for video creation.

### Response
#### Success Response (200)
- **Video** (object) - The created video object.
```

--------------------------------

### GET /organization/data_retention

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves the organization's data retention settings.

```APIDOC
## GET /organization/data_retention

### Description
Retrieves the organization's data retention settings.

### Method
GET

### Endpoint
/organization/data_retention

### Response
#### Success Response (200)
- **OrganizationDataRetention** (object) - The organization's data retention settings.
```

--------------------------------

### get /organization/groups

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all organization groups, with optional filtering and pagination.

```APIDOC
## GET /organization/groups

### Description
Lists all organization groups, with optional filtering and pagination.

### Method
GET

### Endpoint
/organization/groups

### Parameters
#### Query Parameters
- **params** (object) - Optional - Parameters for listing groups (refer to `group_list_params.py`).

### Response
#### Success Response (200)
- **groups** (array of Group) - A list of organization group objects.
```

--------------------------------

### Create a File in a Container (Python)

Source: https://github.com/openai/openai-python/blob/main/api.md

Call the `create` method to upload a new file to a specified container.

```python
client.containers.files.create(container_id, **params) -> FileCreateResponse
```

--------------------------------

### get /organization/groups/{group_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific organization group by its ID.

```APIDOC
## GET /organization/groups/{group_id}

### Description
Retrieves a specific organization group by its ID.

### Method
GET

### Endpoint
/organization/groups/{group_id}

### Parameters
#### Path Parameters
- **group_id** (string) - Required - The ID of the group to retrieve.

### Response
#### Success Response (200)
- **group** (Group) - The retrieved group object.
```

--------------------------------

### GET /organization/admin_api_keys

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a list of admin API keys for the organization.

```APIDOC
## GET /organization/admin_api_keys

### Description
Retrieves a list of admin API keys for the organization.

### Method
GET

### Endpoint
/organization/admin_api_keys

### Parameters
#### Query Parameters
- **params** (object) - Optional - Additional query parameters for filtering and pagination.

### Response
#### Success Response (200)
- **data** (array of AdminAPIKey) - A list of admin API key objects.
- **has_next_page** (boolean) - Indicates if there are more pages of results.

#### Response Example
```json
{
  "data": [
    {
      "id": "admin_key_xyz",
      "created_at": 1678886400
    },
    {
      "id": "admin_key_abc",
      "created_at": 1678790000
    }
  ],
  "has_next_page": false
}
```
```

--------------------------------

### Configure `httpx` Client on a Per-Request Basis

Source: https://github.com/openai/openai-python/blob/main/README.md

Use `client.with_options()` to apply `httpx` client configurations, such as proxies or transports, for specific requests rather than globally.

```python
client.with_options(http_client=DefaultHttpxClient(...))
```

--------------------------------

### List Checkpoint Permissions in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Use the client to list all permissions associated with a specified fine-tuned model checkpoint.

```python
client.fine_tuning.checkpoints.permissions.list(fine_tuned_model_checkpoint, **params)
```

--------------------------------

### Create and Run a Thread with Streaming in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates and runs a thread, streaming events back using an AssistantStreamManager.

```python
client.beta.threads.create_and_run_stream(*args) -> AssistantStreamManager[AssistantEventHandler] | AssistantStreamManager[AssistantEventHandlerT]
```

--------------------------------

### GET /vector_stores/{vector_store_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific vector store by ID.

```APIDOC
## GET /vector_stores/{vector_store_id}

### Description
Retrieves a specific vector store by ID.

### Method
GET

### Endpoint
/vector_stores/{vector_store_id}

### Parameters
#### Path Parameters
- **vector_store_id** (string) - Required - The ID of the vector store to retrieve.

### Response
#### Success Response (200)
- **VectorStore** (object) - The retrieved vector store object.
```

--------------------------------

### Handle Assistant Run Step Events (Python)

Source: https://github.com/openai/openai-python/blob/main/helpers.md

Subscribe to events for the creation, incremental updates (delta), and completion of a RunStep. Useful for tracking the progress of an assistant's execution.

```python
def on_run_step_created(self, run_step: RunStep)
def on_run_step_delta(self, delta: RunStepDelta, snapshot: RunStep)
def on_run_step_done(self, run_step: RunStep)
```

--------------------------------

### get /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists checkpoints for a fine-tuning job.

```APIDOC
## GET /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

### Description
Lists checkpoints for a fine-tuning job.

### Method
GET

### Endpoint
/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

### Parameters
#### Path Parameters
- **fine_tuning_job_id** (string) - Required - The ID of the fine-tuning job.
#### Query Parameters
- **params** (object) - Optional - Parameters for listing checkpoints.

### Response
#### Success Response (200)
- **SyncCursorPage[FineTuningJobCheckpoint]** (array) - A list of fine-tuning job checkpoint objects.
```

--------------------------------

### POST /assistants

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates a new Assistant with specified parameters. This operation allows you to define the Assistant's capabilities, tools, and initial configuration.

```APIDOC
## POST /assistants

### Description
Creates a new Assistant with specified parameters.

### Method
POST

### Endpoint
/assistants

### Request Body
- **params** (object) - Required - Parameters for creating an Assistant, including its name, model, instructions, and tools.
```

--------------------------------

### get /fine_tuning/jobs/{fine_tuning_job_id}/events

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists events for a fine-tuning job.

```APIDOC
## GET /fine_tuning/jobs/{fine_tuning_job_id}/events

### Description
Lists events for a fine-tuning job.

### Method
GET

### Endpoint
/fine_tuning/jobs/{fine_tuning_job_id}/events

### Parameters
#### Path Parameters
- **fine_tuning_job_id** (string) - Required - The ID of the fine-tuning job.
#### Query Parameters
- **params** (object) - Optional - Parameters for listing events.

### Response
#### Success Response (200)
- **SyncCursorPage[FineTuningJobEvent]** (array) - A list of fine-tuning job event objects.
```

--------------------------------

### GET /files/{file_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves information about a specific file by its ID.

```APIDOC
## GET /files/{file_id}

### Description
Retrieves information about a specific file.

### Method
GET

### Endpoint
/files/{file_id}

### Parameters
#### Path Parameters
- **file_id** (string) - Required - The ID of the file to retrieve.

### Response
#### Success Response (200)
- **FileObject** (object) - The file object.
```

--------------------------------

### Create and Run a Thread with Polling in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates and runs a thread, then polls for its completion, returning a Run object.

```python
client.beta.threads.create_and_run_poll(*args) -> Run
```

--------------------------------

### GET /videos/{video_id}/content

Source: https://github.com/openai/openai-python/blob/main/api.md

Downloads the binary content of a specific video.

```APIDOC
## GET /videos/{video_id}/content

### Description
Downloads the binary content of a specific video.

### Method
GET

### Endpoint
/videos/{video_id}/content

### Parameters
#### Path Parameters
- **video_id** (string) - Required - The unique identifier of the video whose content is to be downloaded.

#### Query Parameters
- **params** (object) - Optional - Parameters for downloading video content.

### Response
#### Success Response (200)
- **HttpxBinaryResponseContent** (binary) - The binary content of the video.
```

--------------------------------

### Run Code Linting

Source: https://github.com/openai/openai-python/blob/main/CONTRIBUTING.md

Execute the linting script to check code for style and potential issues using Ruff.

```sh
$ ./scripts/lint
```

--------------------------------

### client.chat.completions.stream()

Source: https://github.com/openai/openai-python/blob/main/helpers.md

This method wraps the `.chat.completions.create(stream=True)` call, providing a more granular event API and automatic accumulation of deltas. It must be used within a context manager.

```APIDOC
## client.chat.completions.stream()

### Description
Initiates a streaming chat completion, providing a granular event API and automatic accumulation of each delta. This method requires usage within a context manager to ensure proper resource management.

### Method Signature
`async with client.chat.completions.stream(model: str, messages: list, **kwargs) as stream:`

### Parameters
- **model** (string) - Required - The ID of the model to use.
- **messages** (list) - Required - A list of messages comprising the conversation so far.

### Usage Example
```python
from openai import AsyncOpenAI

client = AsyncOpenAI()

async with client.chat.completions.stream(
    model='gpt-4o-2024-08-06',
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
) as stream:
    async for event in stream:
        if event.type == 'content.delta':
            print(event.content, flush=True, end='')
```

### Returns
An `AsyncChatCompletionStream` instance (or `ChatCompletionStream` for sync client) which is an async iterator (or iterator) yielding various event types.
```

--------------------------------

### GET /videos/{video_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves a specific video resource by its unique identifier.

```APIDOC
## GET /videos/{video_id}

### Description
Retrieves a specific video resource by its unique identifier.

### Method
GET

### Endpoint
/videos/{video_id}

### Parameters
#### Path Parameters
- **video_id** (string) - Required - The unique identifier of the video to retrieve.

### Response
#### Success Response (200)
- **Video** (object) - The retrieved video object.
```

--------------------------------

### Manual Asynchronous Pagination with Page Control Methods

Source: https://github.com/openai/openai-python/blob/main/README.md

This snippet shows how to use has_next_page(), next_page_info(), and get_next_page() for granular control over fetching successive pages. It allows custom logic before requesting the next set of results.

```python
first_page = await client.fine_tuning.jobs.list(
    limit=20,
)
if first_page.has_next_page():
    print(f"will fetch next page using these details: {first_page.next_page_info()}")
    next_page = await first_page.get_next_page()
    print(f"number of items we just fetched: {len(next_page.data)}")

# Remove `await` for non-async usage.
```

--------------------------------

### get /evals/{eval_id}

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves the details of a specific evaluation by its unique identifier.

```APIDOC
## GET /evals/{eval_id}

### Description
Retrieves the details of a specific evaluation by its unique identifier.

### Method
GET

### Endpoint
/evals/{eval_id}

### Parameters
#### Path Parameters
- **eval_id** (string) - Required - The ID of the evaluation to retrieve.

### Response
#### Success Response (200)
- **response** (EvalRetrieveResponse) - The retrieved evaluation object.
```

--------------------------------

### Activate a Certificate for an Organization Project

Source: https://github.com/openai/openai-python/blob/main/api.md

Activate a specific certificate within an organization project.

```python
client.admin.organization.projects.certificates.activate(project_id, **params) -> SyncPage[CertificateActivateResponse]
```

--------------------------------

### post /organization/projects

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates a new project for the organization.

```APIDOC
## POST /organization/projects

### Description
Creates a new project for the organization.

### Method
POST

### Endpoint
/organization/projects

### Parameters
#### Request Body
- **params** (object) - Optional - Parameters for creating the project.

### Response
#### Success Response (200)
- **Project** (object) - The newly created project object.
```

--------------------------------

### GET /organization/projects/{project_id}/users

Source: https://github.com/openai/openai-python/blob/main/api.md

Lists all users associated with a specific project.

```APIDOC
## GET /organization/projects/{project_id}/users

### Description
Lists all users associated with a specific project.

### Method
GET

### Endpoint
/organization/projects/{project_id}/users

### Parameters
#### Path Parameters
- **project_id** (string) - Required - The ID of the project.

#### Query Parameters
- **params** (object) - Optional - Additional parameters for filtering or pagination.

### Response
#### Success Response (200)
- **SyncConversationCursorPage[ProjectUser]** (object) - A paginated list of project user objects.

```

--------------------------------

### post /completions

Source: https://github.com/openai/openai-python/blob/main/api.md

Creates a completion for the provided prompt and parameters. This endpoint is used to generate text based on a given input.

```APIDOC
## POST /completions

### Description
Creates a completion for the provided prompt and parameters.

### Method
POST

### Endpoint
/completions

### Request Body
- **params** (object) - Required - Parameters for creating the completion.
```

--------------------------------

### get /organization/usage/embeddings

Source: https://github.com/openai/openai-python/blob/main/api.md

Retrieves usage data specifically for embeddings within an organization.

```APIDOC
## GET /organization/usage/embeddings

### Description
Retrieves usage data specifically for embeddings within an organization.

### Method
GET

### Endpoint
/organization/usage/embeddings

### Parameters
This endpoint accepts various parameters for filtering and pagination, but specific details are not provided in the source.

### Response
#### Success Response (200)
Returns a UsageEmbeddingsResponse object containing the requested usage data.
```

--------------------------------

### Create Checkpoint Permission in Python

Source: https://github.com/openai/openai-python/blob/main/api.md

Use the client to create a new permission for a specified fine-tuned model checkpoint.

```python
client.fine_tuning.checkpoints.permissions.create(fine_tuned_model_checkpoint, **params)
```