Skip to main content
fal.ai provides fast inference for 1000+ models including LLMs, image, video, and audio generation.
Provider slug: fal-ai. Requires Backend v1.16.2+ in Model Catalog.

​
Quick Start

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.chat.completions.create(
    model="@fal-ai/fal-ai/flux/schnell",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)
Add a fal.ai provider in Model Catalog with your fal.ai API key, then reference it as @<provider-slug>/<model-id> in requests.
Last modified on May 26, 2026