Infrastructure / Deployment

OpenAI Code Interpreter

Writes and runs Python inside an OpenAI-managed sandbox, exposed as a tool on the Assistants and Responses APIs so a model can compute, analyze attached files, and retry code that fails. Sessions are billed individually and stay active for an hour by default, and attached files are capped at 512 MB. OpenAI documents no isolation mechanism and distributes no runtime.

The same sandbox underlies ChatGPT data analysis, which is the surface the adoption band is attributed to; OpenAI publishes no standalone figure for the tool. Verified 2026-08-13 via the OpenAI Code Interpreter developer documentation.

Openness

1 high confidence

1.0

license: Proprietary
service: proprietary(OpenAI-managed sandbox)
source: closed
isolation: undisclosed
access: API/tool only(no self-host, no open runtime)

Fully proprietary managed code-execution sandbox; OpenAI does not document the isolation mechanism or release any runtime.

https://developers.openai.com/api/docs/assistants/tools/code-interpreter recorded 2026-08-13
Code Interpreter runs Python in a proprietary OpenAI-managed sandbox; $0.03/session; isolation details not disclosed

Adoption

4 low confidence

4.0

Code Interpreter ships inside ChatGPT (advanced data analysis) and the Assistants and Responses APIs; the ChatGPT surface it rides has roughly 1B weekly users. No standalone Code Interpreter usage figure is disclosed, so adoption is attributed to that surface and placed conservatively at 4, on the reading that only a fraction of ChatGPT users invoke code execution, with low confidence given the absence of any per-tool number.

https://developers.openai.com/api/docs/assistants/tools/code-interpreter recorded 2026-08-13
Code Interpreter is a first-class tool in the Assistants/Responses API and underlies ChatGPT data analysis (the surface that drives usage); no usage figure published

Capability

3 low confidence

3.0

Reliable Python-only data-analysis sandbox with iterative retry, but single-language, undisclosed isolation, and session-scoped, narrower than general-purpose deployment sandboxes. Mid-tier; capability detail limited because OpenAI does not document the isolation/scale internals. The docs price the tool at $0.03 per session, cap files at 512 MB, default the session to one hour, and name no isolation mechanism.

https://developers.openai.com/api/docs/assistants/tools/code-interpreter recorded 2026-08-13
Python sandbox, iterative code retry, 512MB files, 1-hour session

Verified 2026-08-13