### GET /videos

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /videos

```markdown
### Parameters

- **limit** (integer, query, optional): Number of items to retrieve
- **order** (OrderEnum, query, optional): Sort order of results by timestamp. Use `asc` for ascending order or `desc` for descending order.
- **after** (string, query, optional): Identifier for the last item from the previous pagination request

### Responses

#### 200 - Success

**VideoListResource**
- **object** (string (list)) (required): The type of object returned, must be `list`. ("list")
- **data** (array (VideoResource)) (required): A list of items
  Array items:
    - **id** (string) (required): Unique identifier for the video job.
    - **object** (string (video)) (required): The object type, which is always `video`. ("video")
    - **model** (string) (required)
    - **status** (string (queued|in_progress|completed|failed)) (required) ("queued"|"in_progress"|"completed"|"failed")
    - **progress** (integer) (required): Approximate completion percentage for the generation task.
    - **created_at** (integer) (required): Unix timestamp (seconds) for when the job was created.
    - **completed_at** (integer) (required): Unix timestamp (seconds) for when the job completed, if finished.
    - **expires_at** (integer) (required): Unix timestamp (seconds) for when the downloadable assets expire, if set.
    - **prompt** (string) (required): The prompt that was used to generate the video.
    - **size** (string (720x1280|1280x720|1024x1792|1792x1024)) (required) ("720x1280"|"1280x720"|"1024x1792"|"1792x1024")
    - **seconds** (string) (required): Duration of the generated clip in seconds. For extensions, this is the stitched total duration.
    - **remixed_from_video_id** (string) (required): Identifier of the source video if this video is a remix.
    - **error** (object) (required): An error that occurred while generating the response.
      - **code** (string) (required): A machine-readable error code that was returned.
      - **message** (string) (required): A human-readable description of the error that was returned.
- **first_id** (string) (required): The ID of the first item in the list.
- **last_id** (string) (required): The ID of the last item in the list.
- **has_more** (boolean) (required): Whether there are more items available.

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/videos?limit=0&order=value&after=string"
```

```

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

### GET /organization/usage/completions

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /organization/usage/completions

```markdown
### Parameters

- **start_time** (integer, query, required): Start time (Unix seconds) of the query time range, inclusive.
- **end_time** (integer, query, optional): End time (Unix seconds) of the query time range, exclusive.
- **bucket_width** (string (1m|1h|1d), query, optional): Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.
- **project_ids** (array (string), query, optional): Return only usage for these projects.
- **user_ids** (array (string), query, optional): Return only usage for these users.
- **api_key_ids** (array (string), query, optional): Return only usage for these API keys.
- **models** (array (string), query, optional): Return only usage for these models.
- **batch** (boolean, query, optional): If `true`, return batch jobs only. If `false`, return non-batch jobs only. By default, return both.

- **group_by** (array (string (project_id|user_id|api_key_id|model|batch|service_tier)), query, optional): Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model`, `batch`, `service_tier` or any combination of them.
- **limit** (integer, query, optional): Specifies the number of buckets to return.
- `bucket_width=1d`: default: 7, max: 31
- `bucket_width=1h`: default: 24, max: 168
- `bucket_width=1m`: default: 60, max: 1440

- **page** (string, query, optional): A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.

### Responses

#### 200 - Usage data retrieved successfully.

**UsageResponse**
- **object** (string (page)) (required) ("page")
- **data** (array (UsageTimeBucket)) (required)
  Array items:
    - **object** (string (bucket)) (required) ("bucket")
    - **start_time** (integer) (required)
    - **end_time** (integer) (required)
    - **results** (array (union)) (required)
      Array items:
        - **object** (string (organization.usage.completions.result)) (required) ("organization.usage.completions.result")
        - **input_tokens** (integer) (required): The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.
        - **input_cached_tokens** (integer): The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.
        - **output_tokens** (integer) (required): The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.
        - **input_audio_tokens** (integer): The aggregated number of audio input tokens used, including cached tokens.
        - **output_audio_tokens** (integer): The aggregated number of audio output tokens used.
        - **num_model_requests** (integer) (required): The count of requests made to the model.
        - **project_id** (string): When `group_by=project_id`, this field provides the project ID of the grouped usage result.
        - **user_id** (string): When `group_by=user_id`, this field provides the user ID of the grouped usage result.
        - **api_key_id** (string): When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result.
        - **model** (string): When `group_by=model`, this field provides the model name of the grouped usage result.
        - **batch** (boolean): When `group_by=batch`, this field tells whether the grouped usage result is batch or not.
        - **service_tier** (string): When `group_by=service_tier`, this field provides the service tier of the grouped usage result.
- **has_more** (boolean) (required)
- **next_page** (string) (required)

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/organization/usage/completions?start_time=0&end_time=0&bucket_width=1d&project_ids=item1,item2&user_ids=item1,item2&api_key_ids=item1,item2&models=item1,item2&batch=true&group_by=item1,item2&limit=0&page=string"
```

```

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

### GET /assistants

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /assistants

```markdown
### Parameters

- **limit** (integer, query, optional): A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

- **order** (string (asc|desc), query, optional): Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.

- **after** (string, query, optional): A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

- **before** (string, query, optional): A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.


### Responses

#### 200 - OK

**ListAssistantsResponse**
- **object** (string) (required) (example: "list")
- **data** (array (AssistantObject)) (required)
  Array items:
    - **id** (string) (required): The identifier, which can be referenced in API endpoints.
    - **object** (string (assistant)) (required): The object type, which is always `assistant`. ("assistant")
    - **created_at** (integer) (required): The Unix timestamp (in seconds) for when the assistant was created.
    - **name** (string) (required): The name of the assistant. The maximum length is 256 characters.

    - **description** (string) (required): The description of the assistant. The maximum length is 512 characters.

    - **model** (string) (required): ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them.

    - **instructions** (string) (required): The system instructions that the assistant uses. The maximum length is 256,000 characters.

    - **tools** (array (union)) (required): A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`.

      Array items:
        - **type** (string (code_interpreter)) (required): The type of tool being defined: `code_interpreter` ("code_interpreter")
    - **tool_resources** (object): A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.

      - **code_interpreter** (object)
        - **file_ids** (array (string)): A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool.

      - **file_search** (object)
        - **vector_store_ids** (array (string)): The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.

    - **metadata** (object) (required): Set of 16 key-value pairs that can be attached to an object. This can be
useful for storing additional information about the object in a structured
format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings
with a maximum length of 512 characters.

    - **temperature** (number): What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
 (example: 1)
    - **top_p** (number): An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.
 (example: 1)
    - **response_format** (string (auto)): `auto` is the default value
 ("auto")
- **first_id** (string) (required) (example: "asst_abc123")
- **last_id** (string) (required) (example: "asst_abc456")
- **has_more** (boolean) (required) (example: false)

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/assistants?limit=20&order=desc&after=string&before=string"
```

```

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

### GET /audio/voice_consents

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

List consent recordings available to your organization for creating custom voices.

See the [custom voices guide](/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.


```markdown
### Parameters

- **after** (string, query, optional): A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

- **limit** (integer, query, optional): A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.


### Responses

#### 200 - OK

**VoiceConsentListResource**
- **object** (string (list)) (required) ("list")
- **data** (array (VoiceConsentResource)) (required)
  Array items:
    - **object** (string (audio.voice_consent)) (required): The object type, which is always `audio.voice_consent`. ("audio.voice_consent")
    - **id** (string) (required): The consent recording identifier. (example: "cons_1234")
    - **name** (string) (required): The label provided when the consent recording was uploaded.
    - **language** (string) (required): The BCP 47 language tag for the consent phrase (for example, `en-US`).
    - **created_at** (integer) (required): The Unix timestamp (in seconds) for when the consent recording was created.
- **first_id** (string)
- **last_id** (string)
- **has_more** (boolean) (required)

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/audio/voice_consents?after=string&limit=20"
```

```

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

### Schema: Audio content part

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Learn about [audio inputs](/docs/guides/audio).


```markdown
## Schema: Audio content part

Learn about [audio inputs](/docs/guides/audio).


**Type:** object

- **type** (string (input_audio)) (required): The type of the content part. Always `input_audio`. ("input_audio")
- **input_audio** (object) (required)
  - **data** (string) (required): Base64 encoded audio data.
  - **format** (string (wav|mp3)) (required): The format of the encoded audio data. Currently supports "wav" and "mp3".
 ("wav"|"mp3")

```

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

### POST /containers

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Creates a container.

```markdown
### Request Body

**Content-Type:** application/json

- **name** (string) (required): Name of the container to create.
- **file_ids** (array (string)): IDs of files to copy to the container.
- **expires_after** (object): Container expiration time in seconds relative to the 'anchor' time.
  - **anchor** (string (last_active_at)) (required): Time anchor for the expiration time. Currently only 'last_active_at' is supported. ("last_active_at")
  - **minutes** (integer) (required)
- **skills** (array (union)): An optional list of skills referenced by id or inline data.
  Array items:
    - **type** (string (skill_reference)) (required): References a skill created with the /v1/skills endpoint. ("skill_reference")
    - **skill_id** (string) (required): The ID of the referenced skill.
    - **version** (string): Optional skill version. Use a positive integer or 'latest'. Omit for default.
- **memory_limit** (string (1g|4g|16g|64g)): Optional memory limit for the container. Defaults to "1g". ("1g"|"4g"|"16g"|"64g")
- **network_policy** (object)
  - **type** (string (disabled)) (required): Disable outbound network access. Always `disabled`. ("disabled")

### Responses

#### 200 - Success

**ContainerResource**
- **id** (string) (required): Unique identifier for the container.
- **object** (string) (required): The type of this object.
- **name** (string) (required): Name of the container.
- **created_at** (integer) (required): Unix timestamp (in seconds) when the container was created.
- **status** (string) (required): Status of the container (e.g., active, deleted).
- **last_active_at** (integer): Unix timestamp (in seconds) when the container was last active.
- **expires_after** (object): The container will expire after this time period.
The anchor is the reference point for the expiration.
The minutes is the number of minutes after the anchor before the container expires.

  - **anchor** (string (last_active_at)): The reference point for the expiration. ("last_active_at")
  - **minutes** (integer): The number of minutes after the anchor before the container expires.
- **memory_limit** (string (1g|4g|16g|64g)): The memory limit configured for the container. ("1g"|"4g"|"16g"|"64g")
- **network_policy** (object): Network access policy for the container.
  - **type** (string (allowlist|disabled)) (required): The network policy mode. ("allowlist"|"disabled")
  - **allowed_domains** (array (string)): Allowed outbound domains when `type` is `allowlist`.

### Example Usage

```bash
curl -X POST "https://api.openai.com/v1/containers" \
  -H "Content-Type: application/json" \
  -d '{
  "name": "string",
  "file_ids": [
    "string"
  ],
  "expires_after": {
    "anchor": "last_active_at",
    "minutes": "0"
  },
  "skills": [
    "value"
  ],
  "memory_limit": "1g",
  "network_policy": "value"
}'
```

```

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

### GET /audio/voice_consents/{consent_id}

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Retrieve consent recording metadata used for creating custom voices.

See the [custom voices guide](/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.


```markdown
### Parameters

- **consent_id** (string, path, required): The ID of the consent recording to retrieve.

### Responses

#### 200 - OK

**VoiceConsentResource**
- **object** (string (audio.voice_consent)) (required): The object type, which is always `audio.voice_consent`. ("audio.voice_consent")
- **id** (string) (required): The consent recording identifier. (example: "cons_1234")
- **name** (string) (required): The label provided when the consent recording was uploaded.
- **language** (string) (required): The BCP 47 language tag for the consent phrase (for example, `en-US`).
- **created_at** (integer) (required): The Unix timestamp (in seconds) for when the consent recording was created.

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/audio/voice_consents/{consent_id}"
```

```

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

### Schema: CreateFineTuningJobRequest

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Schema definition for CreateFineTuningJobRequest

```markdown
## Schema: CreateFineTuningJobRequest

Schema definition for CreateFineTuningJobRequest

**Type:** object

- **model** (string) (required)
- **training_file** (string) (required): The ID of an uploaded file that contains training data.

See [upload file](/docs/api-reference/files/create) for how to upload a file.

Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`.

The contents of the file should differ depending on if the model uses the [chat](/docs/api-reference/fine-tuning/chat-input), [completions](/docs/api-reference/fine-tuning/completions-input) format, or if the fine-tuning method uses the [preference](/docs/api-reference/fine-tuning/preference-input) format.

See the [fine-tuning guide](/docs/guides/model-optimization) for more details.
 (example: "file-abc123")
- **hyperparameters** (object): The hyperparameters used for the fine-tuning job.
This value is now deprecated in favor of `method`, and should be passed in under the `method` parameter.

  - **batch_size** (string (auto)) ("auto")
  - **learning_rate_multiplier** (string (auto)) ("auto")
  - **n_epochs** (string (auto)) ("auto")
- **suffix** (string): A string of up to 64 characters that will be added to your fine-tuned model name.

For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`.

- **validation_file** (string): The ID of an uploaded file that contains validation data.

If you provide this file, the data is used to generate validation
metrics periodically during fine-tuning. These metrics can be viewed in
the fine-tuning results file.
The same data should not be present in both train and validation files.

Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`.

See the [fine-tuning guide](/docs/guides/model-optimization) for more details.
 (example: "file-abc123")
- **integrations** (array (object)): A list of integrations to enable for your fine-tuning job.
  Array items:
    - **type** (string (wandb)) (required) ("wandb")
    - **wandb** (object) (required): The settings for your integration with Weights and Biases. This payload specifies the project that
metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags
to your run, and set a default entity (team, username, etc) to be associated with your run.

      - **project** (string) (required): The name of the project that the new run will be created under.
 (example: "my-wandb-project")
      - **name** (string): A display name to set for the run. If not set, we will use the Job ID as the name.

      - **entity** (string): The entity to use for the run. This allows you to set the team or username of the WandB user that you would
like associated with the run. If not set, the default entity for the registered WandB API key is used.

      - **tags** (array (string)): A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some
default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}".

- **seed** (integer): The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases.
If a seed is not specified, one will be generated for you.
 (example: 42)
- **method** (object): The method used for fine-tuning.
  - **type** (string (supervised|dpo|reinforcement)) (required): The type of method. Is either `supervised`, `dpo`, or `reinforcement`. ("supervised"|"dpo"|"reinforcement")
  - **supervised** (object): Configuration for the supervised fine-tuning method.
    - **hyperparameters** (object): The hyperparameters used for the fine-tuning job.
  - **dpo** (object): Configuration for the DPO fine-tuning method.
  - **reinforcement** (object): Configuration for the reinforcement fine-tuning method.
    - **grader** (object) (required): A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

      - **type** (string (string_check)) (required): The object type, which is always `string_check`. ("string_check")
      - **name** (string) (required): The name of the grader.
      - **input** (string) (required): The input text. This may include template strings.
      - **reference** (string) (required): The reference text. This may include template strings.
      - **operation** (string (eq|ne|like|ilike)) (required): The string check operation to perform. One of `eq`, `ne`, `like`, or `ilike`. ("eq"|"ne"|"like"|"ilike")
    - **hyperparameters** (object): The hyperparameters used for the reinforcement fine-tuning job.
      - **batch_size** (string (auto)) ("auto")
      - **learning_rate_multiplier** (string (auto)) ("auto")
      - **n_epochs** (string (auto)) ("auto")
      - **reasoning_effort** (string (default|low|medium|high)): Level of reasoning effort.
 ("default"|"low"|"medium"|"high")
      - **compute_multiplier** (string (auto)) ("auto")
      - **eval_interval** (string (auto)) ("auto")
      - **eval_samples** (string (auto)) ("auto")
- **metadata** (object): Set of 16 key-value pairs that can be attached to an object. This can be
useful for storing additional information about the object in a structured
format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings
with a maximum length of 512 characters.


```

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

### Schema: FunctionParameters

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. 

Omitting `parameters` defines a function with an empty parameter list.

```markdown
## Schema: FunctionParameters

The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. 

Omitting `parameters` defines a function with an empty parameter list.

**Type:** object


```

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

### POST /containers/{container_id}/files

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Creates a container file.


```markdown
### Parameters

- **container_id** (string, path, required)

### Request Body

**Content-Type:** application/json

- **file_id** (string): Name of the file to create.
- **file** (string (binary)): The File object (not file name) to be uploaded.


**Content-Type:** multipart/form-data

- **file_id** (string): Name of the file to create.
- **file** (string (binary)): The File object (not file name) to be uploaded.


### Responses

#### 200 - Success

**ContainerFileResource**
- **id** (string) (required): Unique identifier for the file.
- **object** (string) (required): The type of this object (`container.file`).
- **container_id** (string) (required): The container this file belongs to.
- **created_at** (integer) (required): Unix timestamp (in seconds) when the file was created.
- **bytes** (integer) (required): Size of the file in bytes.
- **path** (string) (required): Path of the file in the container.
- **source** (string) (required): Source of the file (e.g., `user`, `assistant`).

### Example Usage

```bash
curl -X POST "https://api.openai.com/v1/containers/{container_id}/files" \
  -H "Content-Type: application/json" \
  -d '{
  "file_id": "string",
  "file": "string"
}'
```

```

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

### POST /audio/voices

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Create a custom voice you can use for audio output (for example, in Text-to-Speech and the Realtime API). This requires an audio sample and a previously uploaded consent recording.

See the [custom voices guide](/docs/guides/text-to-speech#custom-voices) for requirements and best practices. Custom voices are limited to eligible customers.


```markdown
### Request Body

**Content-Type:** multipart/form-data

- **name** (string) (required): The name of the new voice.
- **audio_sample** (string (binary)) (required): The sample audio recording file. Maximum size is 10 MiB.

Supported MIME types:
`audio/mpeg`, `audio/wav`, `audio/x-wav`, `audio/ogg`, `audio/aac`, `audio/flac`, `audio/webm`, `audio/mp4`.

- **consent** (string) (required): The consent recording ID (for example, `cons_1234`).

### Responses

#### 200 - OK

**VoiceResource**
- **object** (string (audio.voice)) (required): The object type, which is always `audio.voice`. ("audio.voice")
- **id** (string) (required): The voice identifier, which can be referenced in API endpoints.
- **name** (string) (required): The name of the voice.
- **created_at** (integer) (required): The Unix timestamp (in seconds) for when the voice was created.

### Example Usage

```bash
curl -X POST "https://api.openai.com/v1/audio/voices" \
  -H "Content-Type: application/json" \
  -d '{
  "name": "string",
  "audio_sample": "string",
  "consent": "string"
}'
```

```

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

### Schema: Apply patch create file operation

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Instruction describing how to create a file via the apply_patch tool.

```markdown
## Schema: Apply patch create file operation

Instruction describing how to create a file via the apply_patch tool.

**Type:** object

- **type** (string (create_file)) (required): Create a new file with the provided diff. ("create_file")
- **path** (string) (required): Path of the file to create.
- **diff** (string) (required): Diff to apply.

```

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

### GET /chatkit/threads

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /chatkit/threads

```markdown
### Parameters

- **limit** (integer, query, optional): Maximum number of thread items to return. Defaults to 20.
- **order** (OrderEnum, query, optional): Sort order for results by creation time. Defaults to `desc`.
- **after** (string, query, optional): List items created after this thread item ID. Defaults to null for the first page.
- **before** (string, query, optional): List items created before this thread item ID. Defaults to null for the newest results.
- **user** (string, query, optional): Filter threads that belong to this user identifier. Defaults to null to return all users.

### Responses

#### 200 - Success

**ThreadListResource**
- **object** (string (list)) (required): The type of object returned, must be `list`. ("list")
- **data** (array (ThreadResource)) (required): A list of items
  Array items:
    - **id** (string) (required): Identifier of the thread.
    - **object** (string (chatkit.thread)) (required): Type discriminator that is always `chatkit.thread`. ("chatkit.thread")
    - **created_at** (integer) (required): Unix timestamp (in seconds) for when the thread was created.
    - **title** (string) (required): Optional human-readable title for the thread. Defaults to null when no title has been generated.
    - **status** (object) (required): Indicates that a thread is active.
      - **type** (string (active)) (required): Status discriminator that is always `active`. ("active")
    - **user** (string) (required): Free-form string that identifies your end user who owns the thread.
- **first_id** (string) (required): The ID of the first item in the list.
- **last_id** (string) (required): The ID of the last item in the list.
- **has_more** (boolean) (required): Whether there are more items available.

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/chatkit/threads?limit=0&order=value&after=string&before=string&user=string"
```

```

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

### GET /skills

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /skills

```markdown
### Parameters

- **limit** (integer, query, optional): Number of items to retrieve
- **order** (OrderEnum, query, optional): Sort order of results by timestamp. Use `asc` for ascending order or `desc` for descending order.
- **after** (string, query, optional): Identifier for the last item from the previous pagination request

### Responses

#### 200 - Success

**SkillListResource**
- **object** (string (list)) (required): The type of object returned, must be `list`. ("list")
- **data** (array (SkillResource)) (required): A list of items
  Array items:
    - **id** (string) (required): Unique identifier for the skill.
    - **object** (string (skill)) (required): The object type, which is `skill`. ("skill")
    - **name** (string) (required): Name of the skill.
    - **description** (string) (required): Description of the skill.
    - **created_at** (integer) (required): Unix timestamp (seconds) for when the skill was created.
    - **default_version** (string) (required): Default version for the skill.
    - **latest_version** (string) (required): Latest version for the skill.
- **first_id** (string) (required): The ID of the first item in the list.
- **last_id** (string) (required): The ID of the last item in the list.
- **has_more** (boolean) (required): Whether there are more items available.

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/skills?limit=0&order=value&after=string"
```

```

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

### Schema: Create skill request

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Uploads a skill either as a directory (multipart `files[]`) or as a single zip file.

```markdown
## Schema: Create skill request

Uploads a skill either as a directory (multipart `files[]`) or as a single zip file.

**Type:** object

- **files** (array (string (binary))) (required): Skill files to upload (directory upload) or a single zip file.

```

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

### GET /containers

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Lists containers.

```markdown
### Parameters

- **limit** (integer, query, optional): A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

- **order** (string (asc|desc), query, optional): Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.

- **after** (string, query, optional): A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

- **name** (string, query, optional): Filter results by container name.

### Responses

#### 200 - Success

**ContainerListResource**
- **object** (string (list)) (required): The type of object returned, must be 'list'. ("list")
- **data** (array (ContainerResource)) (required): A list of containers.
  Array items:
    - **id** (string) (required): Unique identifier for the container.
    - **object** (string) (required): The type of this object.
    - **name** (string) (required): Name of the container.
    - **created_at** (integer) (required): Unix timestamp (in seconds) when the container was created.
    - **status** (string) (required): Status of the container (e.g., active, deleted).
    - **last_active_at** (integer): Unix timestamp (in seconds) when the container was last active.
    - **expires_after** (object): The container will expire after this time period.
The anchor is the reference point for the expiration.
The minutes is the number of minutes after the anchor before the container expires.

      - **anchor** (string (last_active_at)): The reference point for the expiration. ("last_active_at")
      - **minutes** (integer): The number of minutes after the anchor before the container expires.
    - **memory_limit** (string (1g|4g|16g|64g)): The memory limit configured for the container. ("1g"|"4g"|"16g"|"64g")
    - **network_policy** (object): Network access policy for the container.
      - **type** (string (allowlist|disabled)) (required): The network policy mode. ("allowlist"|"disabled")
      - **allowed_domains** (array (string)): Allowed outbound domains when `type` is `allowlist`.
- **first_id** (string) (required): The ID of the first container in the list.
- **last_id** (string) (required): The ID of the last container in the list.
- **has_more** (boolean) (required): Whether there are more containers available.

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/containers?limit=20&order=desc&after=string&name=string"
```

```

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

### Schema: Shell action

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

Commands and limits describing how to run the shell tool call.

```markdown
## Schema: Shell action

Commands and limits describing how to run the shell tool call.

**Type:** object

- **commands** (array (string)) (required): Ordered shell commands for the execution environment to run.
- **timeout_ms** (integer): Maximum wall-clock time in milliseconds to allow the shell commands to run.
- **max_output_length** (integer): Maximum number of UTF-8 characters to capture from combined stdout and stderr output.

```

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

### GET /vector_stores

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /vector_stores

```markdown
### Parameters

- **limit** (integer, query, optional): A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

- **order** (string (asc|desc), query, optional): Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.

- **after** (string, query, optional): A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

- **before** (string, query, optional): A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.


### Responses

#### 200 - OK

**ListVectorStoresResponse**

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/vector_stores?limit=20&order=desc&after=string&before=string"
```

```

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

### GET /organization/users

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

API endpoint for GET /organization/users

```markdown
### Parameters

- **limit** (integer, query, optional): A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

- **after** (string, query, optional): A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

- **emails** (array (string), query, optional): Filter by the email address of users.

### Responses

#### 200 - Users listed successfully.

**UserListResponse**
- **object** (string (list)) (required) ("list")
- **data** (array (User)) (required)
  Array items:
    - **object** (string (organization.user)) (required): The object type, which is always `organization.user` ("organization.user")
    - **id** (string) (required): The identifier, which can be referenced in API endpoints
    - **name** (string)
    - **email** (string)
    - **role** (string)
    - **added_at** (integer) (required): The Unix timestamp (in seconds) of when the user was added.
    - **is_default** (boolean): Whether this is the organization's default user.
    - **created** (integer): The Unix timestamp (in seconds) of when the user was created.
    - **user** (object): Nested user details.
      - **object** (string (user)) (required) ("user")
      - **id** (string) (required)
      - **email** (string)
      - **name** (string)
      - **picture** (string)
      - **enabled** (boolean)
      - **banned** (boolean)
      - **banned_at** (integer)
    - **is_service_account** (boolean): Whether the user is a service account.
    - **is_scale_tier_authorized_purchaser** (boolean)
    - **is_scim_managed** (boolean): Whether the user is managed through SCIM.
    - **api_key_last_used_at** (integer)
    - **technical_level** (string)
    - **developer_persona** (string)
    - **projects** (object)
      - **object** (string (list)) (required) ("list")
      - **data** (array (object)) (required)
        Array items:
          - **id** (string)
          - **name** (string)
          - **role** (string)
- **first_id** (string)
- **last_id** (string)
- **has_more** (boolean) (required)

### Example Usage

```bash
curl -X GET "https://api.openai.com/v1/organization/users?limit=20&after=string&emails=item1,item2"
```

```

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

### Schema: Computer use preview

Source: https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

```markdown
## Schema: Computer use preview

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

**Type:** object

- **type** (string (computer_use_preview)) (required): The type of the computer use tool. Always `computer_use_preview`. ("computer_use_preview")
- **environment** (string (windows|mac|linux|ubuntu|browser)) (required) ("windows"|"mac"|"linux"|"ubuntu"|"browser")
- **display_width** (integer) (required): The width of the computer display.
- **display_height** (integer) (required): The height of the computer display.

```