fal Model Routing — 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.

Pick default fal endpoints per job: premium stills, fast drafts, edits, video, lip-sync and campaign work.

• Type: Model · Tools & renderers
• Slug: fal-model-routing
• Status: live
• Publisher: fal (vendor, verified)
• License: MIT
• Source: https://github.com/fal-ai-community/skills/tree/main/skills/model-routing
• Works in: Claude Code, Codex, Cursor, Gemini CLI
• Requires: fal API key (FAL_KEY), genmedia CLI
• Cost: Billed by fal per endpoint call
• Adoption: 460 installs, 256 GitHub stars (skills.sh, 2026-10-26)

What it does

An endpoint-first routing table that fal's production skills use when nobody has named a model. It gives default picks for image generation, text-heavy images, premium stills, fast drafts, editing, top-quality and low-cost video, multi-shot storytelling, native audio and lip-sync, and campaign or UGC work.

Use when

• No model was named for a generation
• Choosing between quality and cost tiers
• Routing campaign or UGC production

Install

• Claude Code: npx skills add fal-ai-community/skills --skill model-routing -a claude-code
• Codex: npx skills add fal-ai-community/skills --skill model-routing -a codex
• Cursor: npx skills add fal-ai-community/skills --skill model-routing -a cursor
• Gemini CLI: npx skills add fal-ai-community/skills --skill model-routing -a gemini-cli

Models it drives: gpt_image_2, nano_banana_pro, nano_banana_2, flux-2, seedream, seedance_2, kling_v3, happy_horse, grok_imagine

Example output

https://skills.varg.ai/previews/fal-model-routing.webp — GPT Image 2 output from fal's GPT Image 2 guide (plastic-letter diner menu board at 5 AM) — openai/gpt-image-2 is model-routing's default for premium and text-heavy stills (credit: fal, https://fal.ai/learn/tools/prompting-gpt-image-2)

More tools & renderers skills

• varg AI: The official varg skill: videos, images, speech and music through one API key, rendered in the cloud or locally.
• Media Download: Save any video by link (X, YouTube, Instagram, TikTok, 1800+ sites) or Pinterest images as references, locally, no key.
• Templates Gallery Ops: Internal runbook for the varg app Templates gallery: publish renders, preview clips, frame-0 posters, shelves.
• HyperFrames CLI: Drive the HyperFrames CLI: scaffold, check, preview, snapshot, edit the timeline, render locally or in the cloud.
• HyperFrames Registry: Pull any of ~450 ready-made blocks into a video as editable source: transitions, titles, captions, charts, 3D.
• HyperFrames Media Use: Find or make every asset a video needs: music, SFX, voiceover, images, logos, avatars, transcripts, grades.

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.

• Claude Code: claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg (skill + hosted MCP)
• Codex, Cursor, Gemini CLI, OpenClaw: npx skills add vargHQ/skills --skill varg-ai -a <agent> -y
• Claude.ai, ChatGPT, any MCP client: connect https://mcp.varg.ai/mcp
• API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt