Documentation

Learn how to run, fine-tune, and deploy AI models with InferGrove.

Quick start

Install the Python SDK and run your first prediction in under a minute:

pip install infergrove

Set your API token:

export INFERGROVE_API_TOKEN=r8_your_token_here

Run a model:

import infergrove

output = infergrove.run(
    "stability/sdxl",
    input={
        "prompt": "a photo of a mountain lake at sunset",
        "width": 1024,
        "height": 1024
    }
)
print(output)
# → ['https://inference.infergrove.com/out/abc123.png']

Authentication

All API requests require an API token. You can find your token in your account settings. Pass it as an environment variable or directly in code:

import infergrove

client = infergrove.Client(api_token="r8_your_token_here")

Next steps

• Browse the model explorer to find models
• Learn about streaming predictions
• Deploy your own model with Cog