Skip to main content
Every model on fal has a Playground where you can try it with real inputs, see outputs, and copy working code in Python, JavaScript, or cURL. Catalog models use the Playground on their model pages. When you deploy your own app, you can test its available endpoints from Testing > Playground in the app dashboard.
Playground for Nano Banana 2 on fal.ai
The Playground is the fastest way to validate a model before writing any integration code. Once you have a result you like, copy the generated code into your project and you are ready to go. If you want to compare multiple models side by side, use the Sandbox instead. For programmatic access, see Client Setup.

Try It

The best way to understand the Playground is to open one. Pick a model and start generating.
ptbZcVWIQ_fXGGHfv8Zez_0ea5ca41bdf143a29e21e30a53120672

Nano Banana 2

Google’s fast image generation and editing
IwzOGSbzp6e8N00QuLtFF_129417bb24f248298e95c3fa2b1b82fb

Veo 3.1

Google DeepMind’s latest video model with sound
SZffdb8layV90JxfN5fkP_d2048a658d9e4dc9973598f3542833a0

ElevenLabs Music

High quality, realistic music generation

What the Playground Shows

Each model page on fal.ai (for example, Nano Banana 2) is organized into tabs. The Playground tab lets you fill in inputs and run the model directly in your browser. The API tab shows the full input and output schemas with type information, so you know exactly what fields are available and what the response looks like. The page also displays pricing, average latency, and ready-to-copy code examples.

Testing a Model

1

Find a model

Browse the model gallery or search for a specific model. Click on it to open its page.
2

Fill in the inputs

The Playground form is auto-generated from the model’s input schema. Required fields are marked, and optional fields have sensible defaults. For models that accept images, video, or audio, you can upload files directly.
3

Run the model

Click Run to submit your request. The result appears below the form, typically within a few seconds.
4

Iterate

Adjust your inputs and run again to refine the result.

Copying Code

Use the input-mode selector to switch from Form or JSON to Python, JavaScript, or cURL. The generated snippet uses your current inputs and the selected endpoint, so you can copy it into your project.
The generated code includes all the parameters you configured in the form, so there is no gap between what you tested and what you ship.

Your Own Apps

For a persistent app created with fal deploy, use the app dashboard as the canonical way to open its Playground. This flow works regardless of which links your installed CLI release prints. If a different account is selected, switch to the personal or team account that owns the app.
1

Open your deployed app

In the Apps dashboard, select the app.
2

Choose an environment

If the app has multiple environments, choose the environment you want to test.
3

Open the Playground

Select Playground under the Testing section of the app sidebar.
4

Select an endpoint

Choose the endpoint you want to test from the endpoint selector. You can move between the app’s available endpoints without leaving the app.
5

Run a request

After you fill in the generated input form, click Run.
To inspect the submitted request after it is recorded, open Requests in the same app. The app Playground uses the same Playground authentication and billing behavior as the standalone experience. Opening it from the dashboard does not change the authentication mode or billing rules you configured for the deployment. Some CLI releases also print a standalone Playground URL after fal deploy. That URL remains valid. The dashboard flow keeps you in the app and provides one place to switch between its endpoints. A Playground URL printed by fal run belongs to that temporary run. Use it while fal run is active. To control how your app’s inputs render in the Playground (image uploaders, hidden fields, field ordering), see Handle Inputs and Outputs. For example, naming a field with an image_url suffix renders it as an image upload widget, and wrapping a field in Hidden() keeps it accessible via API but hides it from the Playground form.

Playground vs Sandbox

The Playground and the Sandbox serve different purposes. The Playground is for testing a single model with specific inputs and copying code. The Sandbox is for comparing multiple models at once, with features like model sets, cost estimates, search across past generations, and shareable links.

More Models to Try

DHb_RgXoXsYLdvzQz6mdn_95e87a44239c43448939b4c382dd957c

Nano Banana 2 Edit

Intelligent image editing
Ji4e0i6Afbeql3Wr5UTz6_ab60b14661424612bf19059e97e996a5

Kling 3.0 Pro

Cinematic image-to-video
0bXyMS_zSKpeaG3LM6ARv_d4ee6acbfd9a4168b012a848c33b154d

Sora 2

OpenAI’s video model with audio
OO8LkBQxwwkEj6SVlP3Bl_2ebfa787acba475b883a9f4ad9106032

Recraft V4 Pro

Professional design visuals
FzzCnGuQNXLOEYuQq8CE8_7afb3290e0de46d5a7e4d13495938e3f

Chatterbox TTS

Natural text-to-speech

Browse All

1,000+ models to explore