# Kimi K3

## Best for

Complex coding and reasoning across long-running tasks

## When not to use

Audio or video. Not the cheapest Flash-class option for short chat or classification.

## Overview

Kimi K3 is Moonshot AI's 2.8-trillion-parameter mixture-of-experts model. It is suited to complex reasoning, long coding sessions, and agentic knowledge work. The model accepts images and has a 1,048,576-token context window.

| | |
| --- | --- |
| API identifier | `kimi-k3` |
| Developer | Moonshot AI |
| Context window | 1,048,576 tokens |
| Supports | text, reasoning, tool-use, image input, vision |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $2.30 | $0.23 | $11.40 |

## Call it

Put `kimi-k3` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).