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

# Kimi K3.1 Pro

> Moonshot's first flagship of the K3.1 series, a post-trained successor to Kimi K3: a 3T-class multimodal reasoning model with major gains in coding, 3D creation and financial modelling. 1M context, image input.

## Overview

Moonshot's first flagship of the K3.1 series, a post-trained successor to Kimi K3: a 3T-class multimodal reasoning model with major gains in coding, 3D creation and financial modelling. 1M context, image input.

## Specs

| Field | Value |
| - | - |
| Model ID | `kimi-k3.1-pro` |
| Best for | Long-horizon agentic coding and reasoning over large inputs |
| Context window | 1.048576M |
| Max output tokens | 944K |
| Input modalities | Text, Image |
| Output modalities | Text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Prompt caching | Yes |
| Vision | Yes |
| Reasoning | Yes |
| Speed | Medium |
| Cost band | Premium |
| Release stage | Stable |

## Pricing

| | Per 1M tokens |
| - | :-: |
| Input | \$2.70 |
| Output | \$13.50 |

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)
```

## Agent query example

Ask the API which models fit, instead of hardcoding an id:

```bash theme={null}
curl "https://kymaapi.com/v1/models?recommended_for=write-code&tools=true&quality_tier=frontier-open"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.