# Grok 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**: 19
- **Vendor**: Grok
- **Base URL**: `https://gptproto.com/v1`
- **Provider page**: https://gptproto.com/model/grok

## 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 |
| --- | --- | --- | --- | --- | --- |
| `grok-4.6` | Grok 4.6 | 500K | $1.2 | $3.6 | [llms.txt](https://gptproto.com/model/grok/grok-4.6/llms.txt) |
| `grok-4.5` | Grok 4.5 | 500K | $1.2 | $3.6 | [llms.txt](https://gptproto.com/model/grok/grok-4.5/llms.txt) |
| `grok-4.3` | Grok 4.3 | 1M | $0.75 | $1.5 | [llms.txt](https://gptproto.com/model/grok/grok-4.3/llms.txt) |
| `grok-4.20-beta-0309-reasoning` | Grok 4.20 Beta 0309 Reasoning | 2M | $0.75 | $1.5 | [llms.txt](https://gptproto.com/model/grok/grok-4.20-beta-0309-reasoning/llms.txt) |
| `grok-4.20-beta-0309-non-reasoning` | Grok 4.20 Beta 0309 Non Reasoning | 2M | $0.75 | $1.5 | [llms.txt](https://gptproto.com/model/grok/grok-4.20-beta-0309-non-reasoning/llms.txt) |
| `grok-4.20-multi-agent-beta-0309` | Grok 4.20 Multi Agent Beta 0309 | 2M | $0.75 | $1.5 | [llms.txt](https://gptproto.com/model/grok/grok-4.20-multi-agent-beta-0309/llms.txt) |
| `grok-code-fast-1` | Grok Code Fast 1 | — | $0.12 | $0.9 | [llms.txt](https://gptproto.com/model/grok/grok-code-fast-1/llms.txt) |
| `grok-4-0709` | Grok 4 0709 | — | $1.8 | $9 | [llms.txt](https://gptproto.com/model/grok/grok-4-0709/llms.txt) |
| `grok-4-1-fast-non-reasoning` | Grok 4.1 Fast Non Reasoning | — | $0.12 | $0.3 | [llms.txt](https://gptproto.com/model/grok/grok-4-1-fast-non-reasoning/llms.txt) |
| `grok-4-1-fast-reasoning` | Grok 4.1 Fast Reasoning | — | $0.12 | $0.3 | [llms.txt](https://gptproto.com/model/grok/grok-4-1-fast-reasoning/llms.txt) |
| `grok-4` | Grok 4 | — | $1.8 | $9 | [llms.txt](https://gptproto.com/model/grok/grok-4/llms.txt) |
| `grok-3-mini` | Grok 3 Mini | — | $0.18 | $0.3 | [llms.txt](https://gptproto.com/model/grok/grok-3-mini/llms.txt) |
| `grok-3-reasoner-r` | Grok 3 Reasoner R | — | $1.8 | $9 | [llms.txt](https://gptproto.com/model/grok/grok-3-reasoner-r/llms.txt) |
| `grok-3-reasoner` | Grok 3 Reasoner | — | — | — | [llms.txt](https://gptproto.com/model/grok/grok-3-reasoner/llms.txt) |
| `grok-3` | Grok 3 | — | $1.8 | $9 | [llms.txt](https://gptproto.com/model/grok/grok-3/llms.txt) |

## Usage example

The snippets below call `grok-4.6`. 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": "grok-4.6",
    "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": "grok-4.6",
  "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: "grok-4.6",
    messages: [
      {
        role: "user",
        content: "Hello",
      },
    ],
  }),
});

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

## Image, video, and audio models

These models use a submit-and-poll API (not OpenAI Chat Completions). Read the per-model guide for the exact endpoint, parameters, and example request.

| Model ID | Name | Type | Price | Guide |
| --- | --- | --- | --- | --- |
| `grok-imagine-image` | Grok Imagine Image | image | $0.012 / run | [llms.txt](https://gptproto.com/model/grok/grok-imagine-image/llms.txt) |
| `grok-imagine-0.9` | Grok Imagine 0.9 | image | $0.135 / run | [llms.txt](https://gptproto.com/model/grok/grok-imagine-0.9/llms.txt) |
| `grok-4-image` | Grok 4 Image | image | $0.042 / run | [llms.txt](https://gptproto.com/model/grok/grok-4-image/llms.txt) |
| `grok-2-image` | Grok 2 Image | image | $0.042 / run | [llms.txt](https://gptproto.com/model/grok/grok-2-image/llms.txt) |

## Additional resources

- [Provider page](https://gptproto.com/model/grok)
- [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`