What people are remixing. Right now.
The recipes others are forking, remixing, and shipping this week.
How the catalog works
What lives in the catalog
The each::labs catalog is the single source of truth for every AI surface you can call through our API:
- Models, image, video, audio, transcription, and embedding endpoints from 40+ providers.
- LLMs, chat models served through the
eachlabs-llm-routerwith one unified contract. - Workflows, multi step recipes that chain several models into one production ready endpoint.
Every entry has a live model card with inputs, outputs, pricing, latency, and a copy-paste cURL / TypeScript snippet.
How to navigate
1. Browse by tab. Switch between Models, LLMs, Workflows, and Trends at the top of the page. 2. Filter by provider or category. The sidebar narrows the grid in real time, no page reload. 3. Search by capability. Type what you want to do ("upscale image", "voice clone", "video lipsync") and the catalog surfaces what fits.
How to ship from a card
Open any card, copy the snippet, swap in your each::labs API key, and call it. The same call signature works in cURL, TypeScript, Python, Go, and any HTTP client.
Why everything is in one place
- One key, one bill. No per provider auth juggling, no rate limit arbitrage, no separate invoices.
- Pinned versions. When a provider ships a new model, we pin the version and keep the old one alive, your code never breaks silently.
- Automatic failover. Configure a backup model and the router fails over the moment your primary returns an error.
- Unified observability. Every call lands in your each::labs traces with latency, cost, and token usage broken out per request.
Production notes
- All endpoints are the same path each::labs uses internally, no preview gates, no waitlists.
- Streaming, tool calls, and structured outputs are passed through to providers as-is where supported.
- Workflows run server-side; you do not need to host any orchestration layer.
About trending AI effects
The short answers. For anything specific to your setup, talk to our team.
Talk to an engineerPlan for your expected volume.The each::labs Trends page is a feed of viral AI effects and templates, such as seasonal portraits, dance videos, cinematic transformations, and outfit swaps, ranked by recent generation volume and packaged as ready-to-run workflows.
Trends rank each workflow and effect by how much it’s being run and how fast that usage is growing over a recent window. The ranking is balanced so a fast-rising new effect can surface alongside a steadily popular one, rather than letting only all-time favorites dominate.
Yes. Every trending effect on each::labs is a pre-built workflow you can run directly with your own photo or prompt, with no setup, no model selection, and no orchestration. Inputs adapt automatically to your asset.
Yes. Each trending each::labs effect is callable through the API and SDKs, so you can ship the same viral templates inside your product as features. Safety filters are tuned for consumer use and can be tightened via API.
Yes. Open any trending effect in the each::labs editor and it becomes your own editable copy, ready for you to change its models, prompts, parameters, or steps. Most effects also expose simple parameters like style, intensity, duration, and aspect ratio you can adjust without rebuilding the pipeline.
A trending effect costs the sum of its underlying model runs at each model’s published price, typically a few cents to around half a dollar per run. The exact price depends on which models the effect chains together.
