# fal.ai integration

> Generative media inference gateway for running hosted image, video, audio, and LLM models via a queue or synchronous HTTP API.

- Authentication: apiKey

## Tools (19)

- **Cancel Queue Request**: Cancel a queued or in-progress request by request_id.
- **Estimate Pricing**: Estimate the cost of planned usage across one or more model endpoints.
- **Generate Image with FLUX1.1 [pro]**: Higher-quality text-to-image generation with the FLUX1.1 [pro] model.
- **Generate Image with FLUX.1 [dev]**: Text-to-image generation with the FLUX.1 [dev] model.
- **Generate Image with Recraft V3**: Text-to-image generation with style control using Recraft V3.
- **Generate or Edit Image with Nano Banana**: Image generation and editing with the Nano Banana (Gemini) model.
- **Generate Speech with ElevenLabs TTS**: Text-to-speech audio generation with ElevenLabs multilingual TTS.
- **Generate Video with Google Veo 3**: Text-to-video generation with audio using Google Veo 3.
- **Generate Video with Kling**: Text-to-video and image-to-video generation with Kling.
- **Generate Video with MiniMax Hailuo**: Text-to-video generation with the MiniMax Hailuo model.
- **Get Account Billing**: Retrieve billing information for the authenticated account.
- **Get Model Pricing**: Retrieve unit pricing for one or more model endpoints.
- **Get Model Usage**: Retrieve usage records, filterable by endpoint, user, and date range.
- **Get Webhook JWKS**: Retrieve the public keys used to verify fal.ai webhook signatures.
- **List Models**: Discover and search fal.ai model endpoints, optionally expanding each model's input schema.
- **Run Model Synchronously**: Run a model on fal.run and get the generated output inline, with no queue or polling.
- **Stream Queue Request Status**: Stream Server-Sent Events of status updates for a queued request.
- **Submit Queue Request (Async)**: Submit a model run to the async queue, poll its status, and fetch the result by request_id.
- **Upload Input File**: Upload local media to the fal.ai CDN and get a public access_url to pass as a model input.

## Related prompts

- [Fill missing Shopify product photos with fal.ai lifestyle shots](https://www.generalinput.com/prompts/fill-missing-shopify-product-photos-with-falai-lifestyle-shots.md)
- [Weekly AI video posted to TikTok and Instagram Reels](https://www.generalinput.com/prompts/weekly-ai-video-posted-to-tiktok-and-instagram-reels.md)
- [Twice-weekly LinkedIn thought-leader posts with matching AI illustrations](https://www.generalinput.com/prompts/twice-weekly-linkedin-thought-leader-posts-with-matching-ai-illustrations.md)
- [Airtable image queue for design teams](https://www.generalinput.com/prompts/airtable-image-queue-for-design-teams.md)

Connect fal.ai in General Input: https://www.generalinput.com/apps/fal-ai