# MoonshotAI models on GPTProto

> One GPTProto API key covers every model listed below. Text models share an OpenAI-compatible API — swap the `model` id. Image / video / audio models use a submit-and-poll API; follow each model's own llms.txt.

## Overview

- **Models**: 3
- **Vendor**: MoonshotAI
- **Base URL**: `https://gptproto.com/v1`
- **Provider page**: https://gptproto.com/model/moonshotai

## Authentication

Every request needs a GPTProto API key in the `Authorization` header. Create one at https://gptproto.com/dashboard/api-key, then export it:

```bash
export GPTPROTO_API_KEY="your-api-key"
```

Header: `Authorization: Bearer $GPTPROTO_API_KEY`. Use `base_url` `https://gptproto.com/v1` with any OpenAI-compatible SDK.

## Text models

Call these with the OpenAI-compatible Chat Completions (or Responses / Messages / Gemini) endpoints. Change only the `model` field.

| Model ID | Name | Context | Input / 1M | Output / 1M | Guide |
| --- | --- | --- | --- | --- | --- |
| `kimi-k3` | Kimi K3 | 1.05M | $2.7 | $13.5 | [llms.txt](https://gptproto.com/model/moonshotai/kimi-k3/llms.txt) |
| `kimi-k2.6` | Kimi K2.6 | 262K | $0.855 | $3.6 | [llms.txt](https://gptproto.com/model/moonshotai/kimi-k2.6/llms.txt) |
| `kimi-k2.5` | Kimi K2.5 | 262K | $0.54 | $2.7 | [llms.txt](https://gptproto.com/model/moonshotai/kimi-k2.5/llms.txt) |

## Usage example

The snippets below call `kimi-k3`. For any other text model in the table, keep the same request and change `"model"`.

```bash
curl --request POST "https://gptproto.com/v1/chat/completions" \
  --header "Authorization: Bearer $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "kimi-k3",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'
```

```python
import os
import requests

url = "https://gptproto.com/v1/chat/completions"
headers = {
  "Authorization": f"Bearer {os.environ['GPTPROTO_API_KEY']}",
  "Content-Type": "application/json"
}
payload = {
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}

response = requests.request("POST", url, headers=headers, json=payload)
print(response.json())
```

```typescript
const response = await fetch("https://gptproto.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.GPTPROTO_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "kimi-k3",
    messages: [
      {
        role: "user",
        content: "Hello",
      },
    ],
  }),
});

const data = await response.json();
console.log(data);
```

## Additional resources

- [Provider page](https://gptproto.com/model/moonshotai)
- [All models](https://gptproto.com/model)
- [API keys](https://gptproto.com/dashboard/api-key)
- [Platform overview for LLMs](https://gptproto.com/llm-full.txt)
- Per-model guide: `https://gptproto.com/model/{vendor}/{model}/llms.txt`