> ## 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.

# AI providers

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

# AI providers

WednesdayAI routes conversations to any supported AI provider. You pick the model; the gateway handles authentication, rotation, retries, and streaming.

## Supported providers

<CardGroup cols={2}>
  <Card title="Anthropic" href="/admin/providers/anthropic" icon="sparkles">
    Claude — Sonnet, Opus, Haiku. Thinking and prompt caching.
  </Card>

  <Card title="OpenAI" href="/admin/providers/openai" icon="bot">
    GPT and Codex. API key or Codex subscription OAuth.
  </Card>

  <Card title="Google" href="/admin/providers/google" icon="google">
    Gemini via AI Studio API key or Vertex AI.
  </Card>

  <Card title="Ollama" href="/admin/providers/ollama" icon="server">
    Run models locally — no API key, full privacy.
  </Card>

  <Card title="OpenRouter" href="/admin/providers/openrouter" icon="shuffle">
    One key, 200+ models, unified billing.
  </Card>

  <Card title="LiteLLM / Bifrost" href="/admin/providers/litellm" icon="network">
    Route through your own LLM proxy.
  </Card>
</CardGroup>

This is a curated subset. WednesdayAI ships the pi-ai catalog, which includes many more built-in providers (xAI, Mistral, Groq, Cerebras, GitHub Copilot, Hugging Face, Z.AI, Vercel AI Gateway, Kilo Gateway, and others) plus custom providers via `models.providers`.

## Authentication

Use onboarding to set up a provider interactively:

```bash theme={"dark"}
openclaw onboard
```

The wizard sets up model and auth for common providers, including Anthropic (API key or `claude setup-token`) and OpenAI Codex (OAuth). For per-provider auth without the full wizard:

```bash theme={"dark"}
openclaw models auth login --provider <provider>        # OAuth providers
openclaw models auth paste-token --provider anthropic   # paste a setup-token
```

For non-interactive hosts and CI, set the provider's environment variable on the gateway host before starting. The daemon reads `~/.openclaw/.env`:

```bash theme={"dark"}
echo 'ANTHROPIC_API_KEY=sk-ant-...' >> ~/.openclaw/.env
```

See [Authentication](/admin/gateway/authentication) for the full credential lookup order, key rotation, and auth profiles.

## Selecting a model

Model references use the **`provider/model`** format, set under a nested `model` object:

```json5 theme={"dark"}
{
  agents: {
    defaults: {
      model: {
        primary: "anthropic/claude-sonnet-4-6",
        fallbacks: ["openai/gpt-5.1-codex"],
      },
    },
  },
}
```

<Warning>
  Always use the nested `model: { primary: "provider/model" }` shape with a provider prefix. A bare string (`model: "claude-sonnet-4-6"`) is deprecated.
</Warning>

If you set `agents.defaults.models`, it becomes the **allowlist** for `/model` and session overrides — a model not in the list is rejected before a reply is generated. Change the model for the current chat with `/model`:

```
/model
/model list
/model openai/gpt-5.2
```

## Checking provider status

```bash theme={"dark"}
openclaw models status          # resolved primary, fallbacks, image model, auth overview
openclaw models list            # configured models (--all for full catalog)
openclaw doctor                 # validate credentials and reachability
```

`openclaw models status --check` exits non-zero when credentials are missing (1) or expiring (2) — wire it into monitoring.

***

**Related:** [Authentication](/admin/gateway/authentication) · [Gateway configuration](/admin/gateway/configuration)