Model schemas in the catalog
Each model in the catalog now shows its full schema, including the normalized parameters and values accepted across all providers, as well as provider-specific fields.Use normalized parameters for portable requests across all providers, or inspect provider-specific fields when you want an upstream option exposed by a particular provider.Developers can fetch the same exact schema from the Models API with?schema=true, so apps and agents can build validated forms and requests from catalog data.Receipts and billing addresses
Billing is easier to reconcile. You can add a billing address for receipts, download PDF receipts for wallet top-ups from the dashboard, and receive the same PDF receipt with top-up confirmation emails.Image upscaling support
Lumenfall now supports dedicated image upscaling models through the same OpenAI-compatible image edit endpoint. Pass an image andscale_factor to route to specialized upscalers such as Topaz, Recraft, Clarity, Real-ESRGAN, and others, with costs available through dry run mode before you run the request.Request management API
You can now inspect and manage account activity from the API. New endpoints let you list requests with filters and cost summaries, list API keys, and purge stored request payloads while preserving request metadata.Alibaba Cloud provider
Alibaba Cloud is now available as a provider, expanding routing coverage for Qwen and Wan models across image and video generation. See the model catalog for the current Alibaba-backed models and modes.Video generation API
Lumenfall now supports video generation through an OpenAI-compatible API. Create text-to-video and image-to-video jobs, poll for completion, cancel jobs, estimate costs with dry run mode, and receive signed webhook notifications when asynchronous video generations complete.Model Advisor
The Model Advisor is now available in beta. Describe what you want to build and it recommends models using Lumenfall’s arena rankings, pricing, speed data, and model catalog details, with inline model cards for the strongest matches.Chrome extension
Generate and edit images directly in your browser with the Lumenfall AI Image Studio Chrome extension. Open the side panel on any page to create images from text prompts, right-click any image on the web to edit it with Lumenfall, or extract page text to brainstorm contextual illustrations. All generated images are saved locally in a built-in gallery.The extension is open source — clone it and build your own tools on top of the Lumenfall API.See the Chrome Extension integration guide for setup and usage.Chat completions endpoint
You can now make LLM calls through Lumenfall using the chat completions endpoint — no need to sign up for a separate text provider or switch base URLs in your SDK. Modern media apps don’t just generate images; they also need LLM calls for prompting, captioning, moderation, and orchestration. Now you can do it all from one platform.Text completions are powered by OpenRouter, so all hundreds of their models are available and all OpenRouter features are fully supported. Use models from OpenAI, Google, Anthropic, Meta, Mistral, and many more providers.Text-to-vector support
Lumenfall now supports text-to-vector (SVG) models. Generate scalable vector graphics through the same OpenAI-compatible API you already use for raster images. Models like Recraft V4 SVG can now return SVG output natively.Playground upgrade
The playground received a major upgrade with new generation controls, model management, and UI improvements.- Generation controls — configure resolution (Standard / HD 2K / Ultra 4K), style, seed, and output format directly from the playground. The aspect ratio picker now honors defaults from loaded examples.
- Model sets and inline editing — curated preset model groups (e.g. “Top Models”, “Speed Round”) drive default panel selections, and clicking a panel’s model name opens a searchable inline picker to swap models on the fly.
- UX improvements — better drag-and-drop with paste support and input image previews, responsive panel actions that collapse into a compact menu at narrow widths, and fixes for image downloads and clipboard copy.
Arena and Google Gemini API
Image arena
Compare image generation models side-by-side with blind voting. See results on the community leaderboard.Try it at lumenfall.ai/arena and lumenfall.ai/leaderboard.Google Gemini API provider
We now support Google’s Gemini API as a provider, in addition to Vertex AI. This gives you more routing options for Google models like Gemini and Imagen. See providers for the full list.llms.py extension
Use Lumenfall image models inside llms.py - both the CLI and the web UI. Generate and edit images with any Lumenfall model in a single command.See the llms.py integration guide for setup and usage.General availability
Lumenfall is now generally available. Access all top image and video generation models through a single, OpenAI-compatible API — including models from the Artificial Analysis Text to Image and Image Editing leaderboards.Each model is backed by multiple providers with automatic failover and zero markup on model costs.Model features like requesting a specific output size or format are normalized across models and providers, so they always just work.OpenAI-compatible API
- Drop-in replacement for OpenAI’s image generation and editing endpoints
- Works with OpenAI SDKs in Python, TypeScript, Go, C#, Java, and Ruby
- Also supports Vercel AI SDK, LiteLLM, and RubyLLM
Multi-provider routing
- Seven providers: Google Vertex AI, Google Gemini API, OpenAI, Replicate, fal.ai, Fireworks AI, and Runware
- Automatic failover when a provider doesn’t respond or returns an error
- Force a specific provider by prefixing the model slug (e.g.,
vertex/gemini-3-pro-image-preview)
Unified model behavior
- Feature emulation ensures all models behave consistently
- Request any size (e.g., “1920x1080”) and we map it to each provider’s and model’s expected format
- Output format conversion (PNG, JPEG, WebP, AVIF) across all providers
- Get responses as URL or base64 (
response_format), regardless of provider support - Standardized error responses following OpenAI conventions
Dashboard
Billing
- Usage-based pricing with no subscriptions or commitments
- Prepaid credits with optional auto top-up
- Dry run mode for cost estimation before generating