Providers
Most of these docs are organized by capability: language models, embeddings, speech, and so on. This page flips that around. If you already use a provider somewhere else and want to know what effect-uai can do with it, find its row and follow the link to the usage page.
Switching providers is always a Layer swap. Each one registers under both its own typed tag and the generic capability tag, so code you write against the generic tag keeps working when you change the backend.
Capability matrix
Three tables, split on lines the library itself draws. Model
capabilities take a model id: you pick a model and quality varies by which
one. Web capabilities are backend services you send requests to.
Runtime capabilities are environments your agent acts inside: a sandbox
it runs code in, a browser it drives. A provider can appear in more than one
(Jina does).
A ✓ links to the usage page for that provider and capability.
Models
| Provider | LLM | Embeddings | Speech | Music |
|---|---|---|---|---|
| OpenAI | ✓ | ✓ | ✓ | |
| ✓ | ✓ | ✓ | ✓ | |
| Anthropic | ✓ | |||
| Mistral | ✓ | ✓ | ||
| ElevenLabs | ✓ | ✓ | ||
| Jina | ✓ | |||
| Inworld | ✓ |
Web
| Provider | Web search | Web reading |
|---|---|---|
| Exa | ✓ | ✓ |
| Perplexity | ✓ | |
| Tavily | ✓ | ✓ |
| Firecrawl | ✓ | |
| Jina | ✓ |
Runtimes
| Provider | Sandbox | Browser |
|---|---|---|
| Microsandbox | ✓ | |
| Deno | ✓ | |
| CDP (Chromium, obscura, hosted browser clouds) | ✓ |
Gateways and protocol adapters
Not every backend is a provider. OpenRouter and Requesty
are routing gateways: one key, hundreds of models, reached through the OpenAI
protocol adapters. Those adapters, Responses and the
legacy Chat Completions base
(@effect-uai/chat-completions), are named for the wire protocol, not a vendor,
so they point at any conforming endpoint via baseUrl.
OpenAI
@effect-uai/openai
GPT models via the Responses API, text embeddings, and speech, all under one
install. The Responses provider also ships standalone as @effect-uai/responses.
@effect-uai/google
Gemini models, Gemini embeddings, Gemini speech, and Lyria music.
- Language model: Google Gemini
- Embeddings: Google Gemini
- Speech: Google Gemini
- Music: Google Lyria
Mistral
@effect-uai/mistral
Mistral chat models plus Voxtral realtime STT and TTS, enough for a full voice pipeline on one brand.
- Language model: Mistral
- Speech: Mistral (Voxtral)
Anthropic
@effect-uai/anthropic
Claude models via the Messages API.
- Language model: Anthropic
ElevenLabs
@effect-uai/elevenlabs
Streaming speech-to-text, text-to-speech, and music generation.
- Speech: ElevenLabs
- Music: ElevenLabs Music
Jina
@effect-uai/jina
Text and multimodal embeddings, including multivector output, plus the Reader for turning URLs into clean markdown.
- Embeddings: Jina
- Web reading: Jina Reader
Inworld
@effect-uai/inworld
Text-to-speech.
- Speech: Inworld
Exa
@effect-uai/exa
Neural web search ranked by relevance score, plus /contents for reading a
URL to clean markdown.
- Web search: Exa
- Web reading: Exa Contents
Perplexity
@effect-uai/perplexity
Fast, current-events web search snippets.
- Web search: Perplexity
Tavily
@effect-uai/tavily
Web search with snippets, scores, and depth control, plus /extract for
reading a URL to clean markdown.
- Web search: Tavily
- Web reading: Tavily Extract
Firecrawl
@effect-uai/firecrawl
JS-rendered pages turned into clean markdown or HTML.
- Web reading: Firecrawl
Microsandbox
@effect-uai/microsandbox
Isolated microVM sandboxes for running model-generated code.
- Sandbox: Microsandbox
Deno
@effect-uai/deno
Sandboxed code execution on the Deno runtime.
- Sandbox: Deno Sandbox
CDP
@effect-uai/browser
One adapter for everything that speaks the Chrome DevTools Protocol, which in practice is the whole browser-automation field: a headless Chromium container, a locally installed Chrome or Edge, a from-scratch engine like obscura, or a hosted browser cloud’s connect URL (Browserbase, Browserless, and the like).
- Browser: Generic CDP