# Kimi K3.1 Pro

## Best for

Frontier open-weight coding agents that run for hours on a million-token context

## When not to use

Audio or video. Not a sub-agent or high-volume pick — pair it with a Flash-class model for short, cheap steps.

## Overview

Kimi K3.1 Pro is Moonshot AI's post-trained successor to Kimi K3: a 2.8-trillion-parameter mixture-of-experts model with 104B parameters active per token. Moonshot reports gains over K3 in coding, factual accuracy, and long-horizon agentic work. It accepts images, calls tools, reasons by default with adjustable effort, and has a 1,048,576-token context window.

| | |
| --- | --- |
| API identifier | `moonshotai/kimi-k3.1-pro` |
| 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 |
| --- | --- | --- |
| $1.70 | $0.20 | $8.50 |

## Call it

Put `moonshotai/kimi-k3.1-pro` 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": "moonshotai/kimi-k3.1-pro",
    "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).