Every LLM, one signature.
357 featured chat models, plus any chat model ID listed on OpenRouter, served through eachlabs-llm-router. Failover, retries, and one bill, no per-provider keys.
LLM
GPT-5.6 Sol
OpenAI
- Router slug
- openai/gpt-5.6-sol
LLM
GPT-5.6 Terra
OpenAI
- Router slug
- openai/gpt-5.6-terra
LLM
GPT-5.6 Luna
OpenAI
- Router slug
- openai/gpt-5.6-luna
LLM
GPT-5.2
OpenAI
- Router slug
- openai/gpt-5.2
LLM
GPT-5.5
OpenAI
- Router slug
- openai/gpt-5.5
- TypesafeLLM
Jev 1.13
Typesafe
- Router slug
- typesafe/jev-1.13
LLM
GPT-5.5 (Online)
OpenAI
- Router slug
- openai/gpt-5.5:online
LLM
GPT-5.4 Mini
OpenAI
- Router slug
- openai/gpt-5.4-mini
LLM
GPT-5.4 Mini (Online)
OpenAI
- Router slug
- openai/gpt-5.4-mini:online
LLM
GPT-5.1
OpenAI
- Router slug
- openai/gpt-5.1
LLM
GPT-4.1
OpenAI
- Router slug
- openai/gpt-4.1
LLM
GPT-4.1 (Online)
OpenAI
- Router slug
- openai/gpt-4.1:online
Six recipes that skip the wiring.
Pre-wired multi-model templates running in production right now. Fork into your account and override anything.
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 LLMs on each::labs
The short answers. For anything specific to your setup, talk to our team.
each::labs features a curated set of frontier and open-weight LLMs, including GPT, Claude, Gemini, Grok, Llama, Mistral, Qwen, and DeepSeek. The OpenAI-compatible LLM Router also accepts any other chat model ID listed on OpenRouter, except free (:free) variants, through the same endpoint and API key.
Yes. Use the each::labs router to pick the cheapest LLM that meets your latency and quality bar, with automatic failover if a provider degrades. Or use each::sense to auto-select the right LLM per prompt.
Yes. The each::labs LLM Router exposes an OpenAI-compatible endpoint, so any SDK or framework that already speaks OpenAI works by pointing it at the each::labs base URL with your each::labs key. You reference any model as provider/model-name and switch models by changing that string.
Yes. Open-weight models such as Llama, Mistral, and DeepSeek are available through the same OpenAI-compatible LLM Router as proprietary frontier models. You switch between an open model and a closed one by changing the model string, and the API and your code stay the same.