Container Files API

Manage files within Code Interpreter containers. Files are created automatically when code interpreter generates outputs (charts, CSVs, images, etc.).

tip

Looking for how to use Code Interpreter? See the Code Interpreter Guide.

Feature	Supported
Cost Tracking	✅
Logging	✅
Supported Providers	openai, azure

Endpoints

Endpoint	Method	Description
/v1/containers/{container_id}/files	POST	Upload file to container
/v1/containers/{container_id}/files	GET	List files in container
/v1/containers/{container_id}/files/{file_id}	GET	Get file metadata
/v1/containers/{container_id}/files/{file_id}/content	GET	Download file content
/v1/containers/{container_id}/files/{file_id}	DELETE	Delete file

LiteLLM Python SDK

Upload Container File

Upload files directly to a container session. This is useful when /chat/completions or /responses sends files to the container but the input file type is limited to PDF. This endpoint lets you work with other file types like CSV, Excel, Python scripts, etc.

upload_container_file.py

from litellm import upload_container_file

# Upload a CSV file
file = upload_container_file(
    container_id="cntr_123...",
    file=("data.csv", open("data.csv", "rb").read(), "text/csv"),
    custom_llm_provider="openai"
)

print(f"Uploaded: {file.id}")
print(f"Path: {file.path}")

Async:

aupload_container_file.py

from litellm import aupload_container_file

file = await aupload_container_file(
    container_id="cntr_123...",
    file=("script.py", b"print('hello world')", "text/x-python"),
    custom_llm_provider="openai"
)

Supported file formats:

• CSV (.csv)
• Excel (.xlsx)
• Python scripts (.py)
• JSON (.json)
• Markdown (.md)
• Text files (.txt)
• And more...

List Container Files

list_container_files.py

from litellm import list_container_files

files = list_container_files(
    container_id="cntr_123...",
    custom_llm_provider="openai"
)

for file in files.data:
    print(f"  - {file.id}: {file.filename}")

Async:

alist_container_files.py

from litellm import alist_container_files

files = await alist_container_files(
    container_id="cntr_123...",
    custom_llm_provider="openai"
)

Retrieve Container File

retrieve_container_file.py

from litellm import retrieve_container_file

file = retrieve_container_file(
    container_id="cntr_123...",
    file_id="cfile_456...",
    custom_llm_provider="openai"
)

print(f"File: {file.filename}")
print(f"Size: {file.bytes} bytes")

Download File Content

retrieve_container_file_content.py

from litellm import retrieve_container_file_content

content = retrieve_container_file_content(
    container_id="cntr_123...",
    file_id="cfile_456...",
    custom_llm_provider="openai"
)

# content is raw bytes
with open("output.png", "wb") as f:
    f.write(content)

Delete Container File

delete_container_file.py

from litellm import delete_container_file

result = delete_container_file(
    container_id="cntr_123...",
    file_id="cfile_456...",
    custom_llm_provider="openai"
)

print(f"Deleted: {result.deleted}")

LiteLLM AI Gateway (Proxy)

Upload File

OpenAI SDK

upload_file.py

from openai import OpenAI

client = OpenAI(
    api_key="sk-<your-litellm-api-key>",
    base_url="http://localhost:4000"
)

file = client.containers.files.create(
    container_id="cntr_123...",
    file=open("data.csv", "rb")
)

print(f"Uploaded: {file.id}")
print(f"Path: {file.path}")

curl

upload_file.sh

curl "http://localhost:4000/v1/containers/cntr_123.../files" \
    -H "Authorization: Bearer $LITELLM_API_KEY" \
    -F file="@data.csv"

List Files

OpenAI SDK

list_files.py

from openai import OpenAI

client = OpenAI(
    api_key="sk-<your-litellm-api-key>",
    base_url="http://localhost:4000"
)

files = client.containers.files.list(
    container_id="cntr_123..."
)

for file in files.data:
    print(f"  - {file.id}: {file.filename}")

curl

list_files.sh

curl "http://localhost:4000/v1/containers/cntr_123.../files" \
    -H "Authorization: Bearer $LITELLM_API_KEY"

Retrieve File Metadata

OpenAI SDK

retrieve_file.py

from openai import OpenAI

client = OpenAI(
    api_key="sk-<your-litellm-api-key>",
    base_url="http://localhost:4000"
)

file = client.containers.files.retrieve(
    container_id="cntr_123...",
    file_id="cfile_456..."
)

print(f"File: {file.filename}")
print(f"Size: {file.bytes} bytes")

curl

retrieve_file.sh

curl "http://localhost:4000/v1/containers/cntr_123.../files/cfile_456..." \
    -H "Authorization: Bearer $LITELLM_API_KEY"

Download File Content

OpenAI SDK

download_content.py

from openai import OpenAI

client = OpenAI(
    api_key="sk-<your-litellm-api-key>",
    base_url="http://localhost:4000"
)

content = client.containers.files.content(
    container_id="cntr_123...",
    file_id="cfile_456..."
)

with open("output.png", "wb") as f:
    f.write(content.read())

curl

download_content.sh

curl "http://localhost:4000/v1/containers/cntr_123.../files/cfile_456.../content" \
    -H "Authorization: Bearer $LITELLM_API_KEY" \
    --output downloaded_file.png

Delete File

OpenAI SDK

delete_file.py

from openai import OpenAI

client = OpenAI(
    api_key="sk-<your-litellm-api-key>",
    base_url="http://localhost:4000"
)

result = client.containers.files.delete(
    container_id="cntr_123...",
    file_id="cfile_456..."
)

print(f"Deleted: {result.deleted}")

curl

delete_file.sh

curl -X DELETE "http://localhost:4000/v1/containers/cntr_123.../files/cfile_456..." \
    -H "Authorization: Bearer $LITELLM_API_KEY"

Parameters

Upload File

Parameter	Type	Required	Description
container_id	string	Yes	Container ID
file	FileTypes	Yes	File to upload. Can be a tuple of (filename, content, content_type), file-like object, or bytes

List Files

Parameter	Type	Required	Description
container_id	string	Yes	Container ID
after	string	No	Pagination cursor
limit	integer	No	Items to return (1-100, default: 20)
order	string	No	Sort order: asc or desc

Retrieve/Delete File

Parameter	Type	Required	Description
container_id	string	Yes	Container ID
file_id	string	Yes	File ID

Response Objects

ContainerFileObject

ContainerFileObject

{
  "id": "cfile_456...",
  "object": "container.file",
  "container_id": "cntr_123...",
  "bytes": 12345,
  "created_at": 1234567890,
  "filename": "chart.png",
  "path": "/mnt/data/chart.png",
  "source": "code_interpreter"
}

ContainerFileListResponse

ContainerFileListResponse

{
  "object": "list",
  "data": [...],
  "first_id": "cfile_456...",
  "last_id": "cfile_789...",
  "has_more": false
}

DeleteContainerFileResponse

DeleteContainerFileResponse

{
  "id": "cfile_456...",
  "object": "container.file.deleted",
  "deleted": true
}

Supported Providers

Provider	Status
OpenAI	✅ Supported
Azure OpenAI	✅ Supported

For Azure, pass custom_llm_provider="azure" with api_base and api_key in the SDK, or send custom-llm-provider: azure to the proxy. A container created on the proxy with an Azure deployment's model returns an ID that routes its file calls to that deployment

Related

• Containers API - Manage containers
• Code Interpreter Guide - Using Code Interpreter with LiteLLM