> ## Documentation Index > Fetch the complete documentation index at: https://fal.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Model APIs > Access 1,000+ production-ready AI models through simple API calls Model APIs gives you instant access to state-of-the-art AI models for image, video, audio, and multimodal generation. Every model is already optimized and production-ready, so you can [authenticate](/documentation/model-apis/authentication) and start generating immediately. Each model runs on fal's infrastructure with automatic scaling, [queue-based reliability](/documentation/model-apis/inference/queue), and [pay-per-use billing](/documentation/model-apis/pricing). You call them the same way whether you use the [Python or JavaScript client](/documentation/model-apis/inference/client-setup) or raw HTTP. If you need to deploy your own model instead, see [Serverless](/documentation/serverless). ## Quick Example Generate an image in three lines of code. Install the client, set your [API key](/documentation/model-apis/authentication), and call a model. ```python Python theme={null} import fal_client result = fal_client.subscribe("fal-ai/nano-banana-2", arguments={ "prompt": "a futuristic cityscape at sunset" }) print(result["images"][0]["url"]) ``` ```javascript JavaScript theme={null} import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/nano-banana-2", { input: { prompt: "a futuristic cityscape at sunset" } }); console.log(result.data.images[0].url); ``` ```bash cURL theme={null} curl -X POST "https://queue.fal.run/fal-ai/nano-banana-2" \ -H "Authorization: Key $FAL_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt": "a futuristic cityscape at sunset"}' ``` The response includes a [CDN URL](/documentation/model-apis/fal-cdn) for the generated image, along with metadata like dimensions and seed. Every model follows the same pattern: send inputs as JSON, receive outputs as JSON with media URLs. ## How It Works Every model on fal is exposed as an HTTP endpoint. You can call it directly, or go through the [queue](/documentation/model-apis/inference/queue) for automatic retries, status tracking, and scaling. There are several calling patterns depending on your use case. **[Direct (`run`)](/documentation/model-apis/inference/synchronous)** sends a synchronous HTTP request to `fal.run` and returns the result directly. This is the simplest approach for quick scripts and prototyping. **[Subscribe](/documentation/model-apis/inference/synchronous)** uses the queue under the hood but handles polling automatically, so it feels synchronous. This is what the Quick Example above uses. **[Asynchronous (`submit`)](/documentation/model-apis/inference/queue)** gives you full control over the queue. Submit a request and return immediately, then poll for status or receive results via [webhook](/documentation/model-apis/inference/webhooks). This is the recommended approach for production workloads with parallel processing. **[Streaming](/documentation/model-apis/inference/streaming)** delivers output progressively as the model generates it. This is useful for LLMs that produce tokens incrementally, or for showing generation progress in a UI. **[`realtime()`](/documentation/model-apis/inference/real-time)** uses WebSockets for persistent connections, bypassing the queue entirely for sub-100ms latency. Only available for models with an explicit real-time endpoint. ## What You Can Generate The [model gallery](https://fal.ai/models) has 1,000+ models spanning several categories. Here are some popular starting points. ### Image Generation and Editing Google's fast image generation and editing model State-of-the-art image generation with realism and typography Enhanced typography and text rendering from BFL Professional design and marketing visuals Intelligent image editing with Google's latest model Targeted edits and complex scene transformations ### Video Generation Google DeepMind's latest video model with sound Cinematic image-to-video with fluid motion Start and end frame animation with scene guidance OpenAI's video model with audio generation Video with audio from images using LTX-2 OpenAI's premium video model with enhanced quality ### Audio and Speech Natural text-to-speech from Resemble AI High-quality multi-voice text-to-speech Multi-speaker dialogue with voice cloning Royalty-free instrumental music generation Professional sound effect generation High quality, realistic music generation Browse 1,000+ models across image, video, audio, 3D, and more Every model page on fal.ai includes a [Playground](/documentation/model-apis/playground) for testing, full API documentation with [input/output schemas](/documentation/model-apis/common-parameters), [pricing](/documentation/model-apis/pricing), and ready-to-copy code examples. ## Next Steps Test and compare models interactively before integrating Learn the different ways to call models Install and configure the fal client for Python, JavaScript, and more Step-by-step tutorials for image, video, and audio generation