BFL API — model skill for tools & renderers

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Integrate the FLUX API correctly: endpoints, async polling, webhooks, rate limits, errors and regions.

What it does

Black Forest Labs' integration guide for the FLUX API: base and model endpoints with pricing, image inputs and multi-reference edits, async polling versus webhooks, rate limits, error handling and regional endpoints, with Python, TypeScript and curl clients. It warns that result URLs expire after 10 minutes.

Use when

Install

Models it drives: flux-2-pro, flux-2-max, flux-2-flex, flux-2-klein, flux-kontext, flux_pro

Example output

https://skills.varg.ai/previews/bfl-api.webp — FLUX.2 multi-reference edit from BFL's FLUX.2 page (the main model behind the API's /v1/flux-2-pro endpoint): children in a photo replaced with animals from five reference images (credit: Black Forest Labs, https://bfl.ai/models/flux-2)

More tools & renderers skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.