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

# Anthropic

> Set up Anthropic (Claude) — complex reasoning, instruction following, and computer-use

# Anthropic (Claude)

```
POST https://api.anthropic.com/v1/messages
```

Uses SSE streaming. Tool calls arrive as `tool_use` content blocks.

Best for: Complex reasoning, detailed instruction following, nuanced tool use, computer-use (screen interaction).

<Note>
  Anthropic is the only provider that supports **computer-use** (screen interaction). If you need Wolffish to drive a browser or desktop UI, you need an Anthropic key.
</Note>

## Getting an API Key

1. Go to [console.anthropic.com](https://console.anthropic.com)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Anthropic

## Models

| Model                      | Context | Modes          | Input / Output (per MTok) | Notes                                                                   |
| -------------------------- | ------- | -------------- | ------------------------- | ----------------------------------------------------------------------- |
| **claude-fable-5**         | 1M      | Off, High, Max | $10.00 / $50.00           | Frontier reasoning. Cached: \$1.00/MTok.                                |
| claude-opus-4-8            | 1M      | Off, High, Max | $5.00 / $25.00            | Strong reasoning. Cached: \$0.50/MTok.                                  |
| claude-opus-4-7            | 1M      | Off, High, Max | $5.00 / $25.00            | Strong reasoning. Cached: \$0.50/MTok.                                  |
| claude-sonnet-4-6          | 1M      | Off, High, Max | $3.00 / $15.00            | Best balance of quality and cost. Cached: \$0.30/MTok.                  |
| claude-opus-4-6            | 1M      | Off, High, Max | $5.00 / $25.00            | Reasoning. Cached: \$0.50/MTok.                                         |
| claude-opus-4-5-20251101   | 200K    | Off, High, Max | $5.00 / $25.00            | Previous gen. Cached: \$0.50/MTok.                                      |
| claude-sonnet-4-5-20250929 | 200K    | Off, High, Max | $3.00 / $15.00            | Previous gen. Cached: \$0.30/MTok.                                      |
| claude-haiku-4-5-20251001  | 200K    | Off, High      | $1.00 / $5.00             | Fast and cheap. Not recommended for agentic tasks. Cached: \$0.10/MTok. |
| claude-opus-4-1-20250805   | 200K    | Off, High, Max | $15.00 / $75.00           | Legacy. Cached: \$1.50/MTok.                                            |

## Reasoning modes

The **brain icon** next to the message box controls how this model reasons. Click it to cycle through the modes the selected model supports. Two separate ideas combine here:

### Thinking — *whether* the model reasons

* **Off** — the model answers immediately. Fastest and cheapest; ideal for simple, direct tasks.
* **On** — the model first works through the problem in a dedicated reasoning pass before replying. Slower and uses more tokens, but markedly more accurate on multi-step, logical, or ambiguous tasks.

### Effort — *how hard* it thinks

Only effort-capable models expose this; it applies once thinking is on.

* **High** — standard reasoning depth. The right default for most agentic work.
* **Max** — the model reasons longer and deeper for the hardest problems. More tokens and latency in exchange for higher quality on complex work.

### Button states

| State | Colour | Meaning                         |
| ----- | ------ | ------------------------------- |
| Off   | gray   | Thinking off — direct answer    |
| On    | blue   | Thinking on — no effort control |
| High  | purple | Thinking on, standard effort    |
| Max   | orange | Thinking on, maximum effort     |

Each model shows only the states it genuinely supports. If a model always reasons (can't be turned off) or has no effort control, the button reflects that and locks where there's nothing to change. Wolffish remembers your choice per model.

**On Anthropic:** Opus, Sonnet and Fable models support Off / High / Max; Haiku supports Off / High. On the newest models (Opus 4-8 and 4-7) thinking is adaptive — the model chooses its own depth — and Anthropic does not return the reasoning text; 4-6 and earlier stream their reasoning.

<Note>
  All models support tool calling with no hard tool-count limit. Anthropic uses ephemeral prefix caching for cost savings on repeated context.
</Note>