OpenRouter serves image models, including FLUX 3 Image Klein
Melvin Vivas · X post · 2026-10-16 · Open on X
Topics: Industry Trends & Job Market, AI Dev Tools & Productivity · Level: beginner
Summary
A reminder that OpenRouter serves image and video models as well as LLMs. The quoted post lists new Black Forest Labs releases on OpenRouter: FLUX 3 Image Klein, a cheaper FLUX Video Upscale, and 4K text-to-video with FLUX 3 Video.
Key points
- OpenRouter serves image models, not just text LLMs
- FLUX 3 Image Klein is an open-weights image model that runs on one consumer GPU
- An improved FLUX Video Upscale (early access) turns any video into 4K for $0.28/s, down from $0.59/s
- FLUX 3 Video can now generate 4K videos from a prompt
- All of these come from Black Forest Labs (@bfl_ai)
Resources mentioned
- OpenRouter · tool · openrouter.ai · free
A single OpenAI-compatible API that routes requests to hundreds of models from many providers, with one bill and model fallbacks.
Also in: Stealth Model 'Space Bunny' Revealed as MiniMax M3.1 Flash (Melvin Vivas on X · notes), NVIDIA Nemotron 3.5 Super VL now on OpenRouter (Melvin Vivas on X · notes), Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter (Melvin Vivas on X · notes), Coworker: An Open-Source Personal AI Assistant Desktop App (Not a Coding Agent) (Melvin Vivas on X · notes) and 53 more - FLUX 3 Image Klein · tool · bfl.ai · free
A 5.6B-parameter image generation and editing model from Black Forest Labs, with open weights for base and distilled versions.
Also in: FLUX 3 Image Klein: Open-Weights Image Model Now Supported in ComfyUI (Melvin Vivas on X · notes) - FLUX Video Upscale · tool · bfl.ai · paid
Black Forest Labs' service that upscales any video to 4K. - Flux 3 Video · tool · check price
Black Forest Labs' video-generation model that can now create 4K videos from a text prompt.
Also in: ComfyUI Templates: Chain Ready-Made Workflows Instead of Building From Scratch (Melvin Vivas on X · notes) - Black Forest Labs · website · bfl.ai · check price
The lab behind the FLUX image models; the speaker's team, which published Self-Flow.
Also in: FLUX 3 Image Klein: Open-Weights Image Model Now Supported in ComfyUI (Melvin Vivas on X · notes), Martin Scorsese Joins Black Forest Labs: Storyboarding with FLUX (Melvin Vivas on X · notes), Martin Scorsese Storyboards a Scene with Black Forest Labs' FLUX (Melvin Vivas on X · notes), Self-Flow: Training Multimodal Generative Models Without an External Encoder (Melvin Vivas on X · notes)
Try this
- Try FLUX 3 Image Klein through OpenRouter or run it locally on a consumer GPU
More in Industry Trends & Job Market
- Why Grok Bot Could Be the Next "ChatGPT Moment" for Personal AI Assistants
- Liquid AI releases d1-ultra decision model
- NVIDIA Nemotron 3.5 Super VL now on OpenRouter
- Grok Bot is catching on with non-technical users
- NVIDIA opens pre-orders for RTX Spark Windows laptops
- Meta Releases Muse Spark Open Weights, Optimized for Mac Studio