Anthropic builds the Claude model family. Genesis supports two auth routes:

• API key — direct Anthropic API access with usage-based billing (anthropic/* models)
• Claude CLI — reuse an existing Claude CLI login on the same host

Getting started

API key

**Best for:** standard API access and usage-based billing.

Get your API key

    Create an API key in the [Anthropic Console](https://console.anthropic.com/).

Run onboarding

    ```bash
    genesis onboard
    # choose: Anthropic API key
    ```

    Or pass the key directly:

    ```bash
    genesis onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
    ```

Verify the model is available

    ```bash
    genesis models list --provider anthropic
    ```
  




### Config example

```json5
{
  env: { ANTHROPIC_API_KEY: "sk-ant-..." },
  agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}
```

Claude CLI

**Best for:** reusing an existing Claude CLI login without a separate API key.

Ensure Claude CLI is installed and logged in

    Verify with:

    ```bash
    claude --version
    ```

Run onboarding

    ```bash
    genesis onboard
    # choose: Claude CLI
    ```

    Genesis detects and reuses the existing Claude CLI credentials.

Verify the model is available

    ```bash
    genesis models list --provider anthropic
    ```
  




<div class="callout note">
Setup and runtime details for the Claude CLI backend are in [CLI Backends](/gateway/cli-backends).
</div>

<div class="callout tip">
If you want the clearest billing path, use an Anthropic API key instead. Genesis also supports subscription-style options from [OpenAI Codex](/providers/openai), [Qwen Cloud](/providers/qwen), [MiniMax](/providers/minimax), and [Z.AI / GLM](/providers/glm).
</div>

Thinking defaults (Claude 4.6)

Claude 4.6 models default to adaptive thinking in Genesis when no explicit thinking level is set.

Override per-message with /think:<level> or in model params:

{
  agents: {
    defaults: {
      models: {
        "anthropic/claude-opus-4-6": {
          params: { thinking: "adaptive" },
        },
      },
    },
  },
}

Prompt caching

Genesis supports Anthropic's prompt caching feature for API-key auth.

{
  agents: {
    defaults: {
      models: {
        "anthropic/claude-opus-4-6": {
          params: { cacheRetention: "long" },
        },
      },
    },
  },
}

Per-agent cache overrides

Use model-level params as your baseline, then override specific agents via `agents.list[].params`:

```json5
{
  agents: {
    defaults: {
      model: { primary: "anthropic/claude-opus-4-6" },
      models: {
        "anthropic/claude-opus-4-6": {
          params: { cacheRetention: "long" },
        },
      },
    },
    list: [
      { id: "research", default: true },
      { id: "alerts", params: { cacheRetention: "none" } },
    ],
  },
}
```

Config merge order:

1. `agents.defaults.models["provider/model"].params`
2. `agents.list[].params` (matching `id`, overrides by key)

This lets one agent keep a long-lived cache while another agent on the same model disables caching for bursty/low-reuse traffic.

Bedrock Claude notes

- Anthropic Claude models on Bedrock (`amazon-bedrock/*anthropic.claude*`) accept `cacheRetention` pass-through when configured.
- Non-Anthropic Bedrock models are forced to `cacheRetention: "none"` at runtime.
- API-key smart defaults also seed `cacheRetention: "short"` for Claude-on-Bedrock refs when no explicit value is set.

Advanced configuration

Fast mode

Genesis's shared `/fast` toggle supports direct Anthropic traffic (API-key and OAuth to `api.anthropic.com`).

| Command | Maps to |
|---------|---------|
| `/fast on` | `service_tier: "auto"` |
| `/fast off` | `service_tier: "standard_only"` |

```json5
{
  agents: {
    defaults: {
      models: {
        "anthropic/claude-sonnet-4-6": {
          params: { fastMode: true },
        },
      },
    },
  },
}
```

<div class="callout note">
- Only injected for direct `api.anthropic.com` requests. Proxy routes leave `service_tier` untouched.
- Explicit `serviceTier` or `service_tier` params override `/fast` when both are set.
- On accounts without Priority Tier capacity, `service_tier: "auto"` may resolve to `standard`.
</div>

Media understanding (image and PDF)

The bundled Anthropic plugin registers image and PDF understanding. Genesis
auto-resolves media capabilities from the configured Anthropic auth — no
additional config is needed.

| Property       | Value                |
| -------------- | -------------------- |
| Default model  | `claude-opus-4-6`    |
| Supported input | Images, PDF documents |

When an image or PDF is attached to a conversation, Genesis automatically
routes it through the Anthropic media understanding provider.

1M context window (beta)

Anthropic's 1M context window is beta-gated. Enable it per model:

```json5
{
  agents: {
    defaults: {
      models: {
        "anthropic/claude-opus-4-6": {
          params: { context1m: true },
        },
      },
    },
  },
}
```

Genesis maps this to `anthropic-beta: context-1m-2025-08-07` on requests.

<div class="callout warning">
Requires long-context access on your Anthropic credential. Legacy token auth (`sk-ant-oat-*`) is rejected for 1M context requests — Genesis logs a warning and falls back to the standard context window.
</div>

Claude Opus 4.7 1M context

`anthropic/claude-opus-4.7` and its `claude-cli` variant have a 1M context
window by default — no `params.context1m: true` needed.

Troubleshooting

401 errors / token suddenly invalid

Anthropic token auth expires and can be revoked. For new setups, use an Anthropic API key instead.

Details

Anthropic auth is **per agent** — new agents do not inherit the main agent's keys. Re-run onboarding for that agent (or configure an API key on the gateway host), then verify with `genesis models status`.

Details

Run `genesis models status` to see which auth profile is active. Re-run onboarding, or configure an API key for that profile path.

No available auth profile (all in cooldown)

Check `genesis models status --json` for `auth.unusableProfiles`. Anthropic rate-limit cooldowns can be model-scoped, so a sibling Anthropic model may still be usable. Add another Anthropic profile or wait for cooldown.

Related

• Model selection Choosing providers, model refs, and failover behavior.

• CLI backends Claude CLI backend setup and runtime details.

• Prompt caching How prompt caching works across providers.

• OAuth and auth Auth details and credential reuse rules.