gpt-oss

library0.0.9pypypi✓ verified 82d ago

gpt-oss is a collection of reference inference implementations for GPT models, published by OpenAI. Current version is 0.0.9, requiring Python >=3.12. It is in early development with weekly releases.

llm-agents ai-ml

pip install gpt-oss

package ↗

INSTALL

IMPORT

SIG · GPT-OSS

gpt-oss

llm-agentspythonv0.0.9

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

GPTInference

✓ import gpt_oss

✗ from gpt_oss import GPTInference

Initialize GPTInference with an API key from environment variable and generate a response.

from gpt_oss import GPTInference import os api_key = os.environ.get('OPENAI_API_KEY', '') model = GPTInference(model_name='gpt-3.5-turbo', api_key=api_key) response = model.generate("Hello, world!") print(response)

Debug

Known issues

breakingPython >=3.12 is required. Older versions will fail to install or import.

fix

Upgrade Python to 3.12 or later.

affects: <0.0.9

deprecatedThe `generate` method's argument `max_tokens` has been renamed to `max_new_tokens` in v0.0.9.

fix

Use `max_new_tokens` instead of `max_tokens`.

affects: >=0.0.7

gotchaImport uses underscore (`gpt_oss`) not hyphen (`gpt-oss`).

fix

Use `from gpt_oss import ...`

affects: all

Upgrade

Version history

0.0.9latest on PyPI · released Jan 13, 2026

Audit

Dependencies

numpyrequiredArray operations and data handling

torchrequiredPyTorch tensors and neural network modules

Agent activity

19 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/gpt-oss/ ↗