> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Providers

> Connect WednesdayAI to Claude, GPT, Gemini, local models, and proxies — one gateway, any model.

# Model Providers

WednesdayAI can use many LLM providers. Pick a provider, authenticate, then set the
default model as `provider/model`.

Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See [Channels](https://docs.wednesdayai.dev/next/admin/channels.md).

## Quick start

1. Authenticate with the provider (usually via `wednesdayai onboard`).
2. Set the default model:

```json5 theme={"dark"}
{
  agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}
```

## Provider docs

* [Amazon Bedrock](https://docs.wednesdayai.dev/next/admin/providers/bedrock.md)
* [Anthropic (API + Claude Code CLI)](https://docs.wednesdayai.dev/next/admin/providers/anthropic.md)
* [Cloudflare AI Gateway](https://docs.wednesdayai.dev/next/admin/providers/cloudflare-ai-gateway.md)
* [GLM models](https://docs.wednesdayai.dev/next/admin/providers/glm.md)
* [Hugging Face (Inference)](https://docs.wednesdayai.dev/next/admin/providers/huggingface.md)
* [Kilocode](https://docs.wednesdayai.dev/next/admin/providers/kilocode.md)
* [LiteLLM (unified gateway)](https://docs.wednesdayai.dev/next/admin/providers/litellm.md)
* [MiniMax](https://docs.wednesdayai.dev/next/admin/providers/minimax.md)
* [Mistral](https://docs.wednesdayai.dev/next/admin/providers/mistral.md)
* [Moonshot AI (Kimi + Kimi Coding)](https://docs.wednesdayai.dev/next/admin/providers/moonshot.md)
* [NVIDIA](https://docs.wednesdayai.dev/next/admin/providers/nvidia.md)
* [Ollama (local models)](https://docs.wednesdayai.dev/next/admin/providers/ollama.md)
* [OpenAI (API + Codex)](https://docs.wednesdayai.dev/next/admin/providers/openai.md)
* [OpenCode Zen](https://docs.wednesdayai.dev/next/admin/providers/opencode.md)
* [OpenRouter](https://docs.wednesdayai.dev/next/admin/providers/openrouter.md)
* [Qianfan](https://docs.wednesdayai.dev/next/admin/providers/qianfan.md)
* [Qwen (OAuth)](https://docs.wednesdayai.dev/next/admin/providers/qwen.md)
* [Together AI](https://docs.wednesdayai.dev/next/admin/providers/together.md)
* [Vercel AI Gateway](https://docs.wednesdayai.dev/next/admin/providers/vercel-ai-gateway.md)
* [Venice (Venice AI, privacy-focused)](https://docs.wednesdayai.dev/next/admin/providers/venice.md)
* [vLLM (local models)](https://docs.wednesdayai.dev/next/admin/providers/vllm.md)
* [Xiaomi](https://docs.wednesdayai.dev/next/admin/providers/xiaomi.md)
* [Z.AI](https://docs.wednesdayai.dev/next/admin/providers/zai.md)

## Transcription providers

Audio/image/video understanding providers ship as plugin extensions, disabled by default. See
[Media Understanding](https://docs.wednesdayai.dev/next/users/nodes/media-understanding.md#provider-extensions) for the full vendor list
(OpenAI, Groq, Deepgram, Google, Mistral, ElevenLabs, OpenRouter, DeepInfra, Bifrost, and more)
and how to enable one.

* [Deepgram (audio transcription)](https://docs.wednesdayai.dev/next/admin/providers/deepgram.md)

## Streaming voice conversation providers

The live, cascaded voice conversation loop behind the `/v2/client` web client's Dictate and Voice
mode controls uses its own streaming speech-to-text/text-to-speech provider seam, separate from
the transcription providers above. See
[Voice conversation sessions](https://docs.wednesdayai.dev/next/users/talk/realtime-voice-conversation).

* [ElevenLabs (streaming voice)](https://docs.wednesdayai.dev/next/admin/providers/elevenlabs.md)

## Community tools

* [Claude Max API Proxy](https://docs.wednesdayai.dev/next/admin/providers/claude-max-api-proxy.md) - Community proxy for Claude subscription credentials (verify Anthropic policy/terms before use)

For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration,
see [Model providers](https://docs.wednesdayai.dev/next/developers/concepts/model-providers.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.