Metadata-Version: 2.4
Name: infermion
Version: 0.1.0
Summary: Official Python SDK for Infermion
Author: Infermion
Project-URL: Homepage, https://pypi.org/project/infermion/
Project-URL: Documentation, https://pypi.org/project/infermion/#description
Keywords: ai,cloud,gpu,inference,infermion,sdk
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Typing :: Typed
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.27.0
Requires-Dist: pydantic>=2.8.0

# Infermion Python SDK

The official synchronous and asynchronous Python client for Infermion.

```python
from infermion import Infermion

client = Infermion(api_token="...")
for deployment in client.deployments.list():
    print(deployment.id, deployment.status)

context = client.run.context(deployment="dep_prod")
response = client.run.chat(
    deployment="dep_prod",
    model="chat",  # served name, not a provider/model ID
    prompt="Explain tensor parallelism",
)

# Long-running tasks can be detached without changing deployment/model state.
job = client.run.submit(
    deployment="dep_prod",
    model="image",
    task="image_generation",
    input=[{"role": "user", "content": "A nebula"}],
)
```

The SDK never opens a browser or prompts. Use `infermion login` from the
native `infermion` terminal application for interactive authentication.

`Infermion` and `AsyncInfermion` expose market/planning, account models,
dedicated deployments and model lifecycle, model-aware run, endpoints, keys,
connections, volumes, billing, jobs, events, extensions, and plugins. Use
`InferenceClient`/`AsyncInferenceClient` with a separately scoped endpoint API
key for stable endpoint data-plane calls.
