> ## 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.

# Kimi

> Set up Kimi (Moonshot AI) — powerful reasoning with long-context support

# Kimi (Moonshot AI)

```
POST https://api.moonshot.ai/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision (base64 images) and reasoning content.

Best for: Agentic workflows, long-context tasks, reasoning-heavy workloads, and cost-efficient daily automations.

## Getting an API Key

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

## Models

| Model                    | Context | Modes   | Input / Output (per MTok) | Cached | Notes                                   |
| ------------------------ | ------- | ------- | ------------------------- | ------ | --------------------------------------- |
| **kimi-k2.6**            | 256K    | Off, On | $0.95 / $4.00             | \$0.16 | Latest flagship. Vision + reasoning.    |
| kimi-k2.5                | 256K    | Off, On | $0.60 / $3.00             | \$0.10 | Vision + reasoning.                     |
| kimi-k2.7-code           | 256K    | On      | — / —                     | —      | Code-focused. Reasoning always on.      |
| kimi-k2.7-code-highspeed | 256K    | On      | — / —                     | —      | Fast code variant. Reasoning always on. |
| moonshot-v1-auto         | 128K    | —       | $1.00 / $3.00             | —      | Auto-selects context tier.              |
| moonshot-v1-128k         | 128K    | —       | $2.00 / $5.00             | —      | Long-context.                           |
| moonshot-v1-32k          | 32K     | —       | $1.00 / $3.00             | —      | Mid-context.                            |
| moonshot-v1-8k           | 8K      | —       | $0.20 / $2.00             | —      | Short-context, cheapest.                |

## 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 Kimi:** k2.x models are On / Off. The k2.x-code variants reason always-on (locked on). The older moonshot-v1 models don't reason.

<Note>
  Kimi K2.6 sits between the budget Chinese providers (DeepSeek, MiMo) and the premium Western providers (Anthropic, OpenAI) on price — offering strong reasoning at a mid-range cost. See [Choosing a Provider](/configuration/providers#choosing-a-provider) for guidance on when to use which tier.
</Note>