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

# Demo chat

> Try AI models without deploying an agent. No authentication required.

# Demo chat

The demo chat endpoint lets you interact with AI models without signing up or deploying an agent. Requests are rate-limited by IP address.

## List available models

```http theme={"dark"}
GET /api/demo/chat
```

No authentication required. Returns the list of models available in demo mode.

### Response (200)

```json theme={"dark"}
{
  "models": [
    { "id": "xiaomi/mimo-v2-pro", "name": "MiMo-V2-Pro", "provider": "Xiaomi" },
    { "id": "anthropic/claude-sonnet-4.5", "name": "Claude Sonnet 4.5", "provider": "Anthropic" },
    { "id": "openai/gpt-4o", "name": "GPT-4o", "provider": "OpenAI" },
    { "id": "google/gemini-2.5-flash", "name": "Gemini 2.5 Flash", "provider": "Google" },
    { "id": "deepseek/deepseek-r1", "name": "DeepSeek R1", "provider": "DeepSeek" },
    { "id": "minimax/minimax-chat", "name": "MiniMax M2.7", "provider": "MiniMax" }
  ],
  "mode": "demo",
  "message": "Welcome to Agentbot Demo - try AI models without deploying"
}
```

| Field               | Type   | Description                              |
| ------------------- | ------ | ---------------------------------------- |
| `models`            | array  | Available demo models                    |
| `models[].id`       | string | Model identifier to use in POST requests |
| `models[].name`     | string | Human-readable model name                |
| `models[].provider` | string | AI provider name                         |
| `mode`              | string | Always `demo`                            |
| `message`           | string | Welcome message                          |

## Send a demo message

```http theme={"dark"}
POST /api/demo/chat
```

No authentication required. Rate-limited by IP address.

### Request body

| Field          | Type   | Required | Description                                                                                                    |
| -------------- | ------ | -------- | -------------------------------------------------------------------------------------------------------------- |
| `message`      | string | Yes      | Message to send                                                                                                |
| `model`        | string | No       | Model ID from the models list. Defaults to `xiaomi/mimo-v2-pro`.                                               |
| `mode`         | string | No       | Chat mode identifier                                                                                           |
| `conversation` | array  | No       | Previous conversation messages for context. Only `user`-role messages are retained (max 4000 characters each). |

### Example request

```json theme={"dark"}
{
  "message": "What plans does Agentbot offer?",
  "model": "openai/gpt-4o",
  "conversation": [
    { "role": "user", "content": "Tell me about Agentbot" }
  ]
}
```

### Response (200)

```json theme={"dark"}
{
  "id": "gen-abc123",
  "model": "openai/gpt-4o",
  "message": "Agentbot offers four plans: Solo, Collective, Label, and Network...",
  "usage": {
    "prompt_tokens": 450,
    "completion_tokens": 120,
    "total_tokens": 570
  },
  "done": true
}
```

| Field                     | Type    | Description                              |
| ------------------------- | ------- | ---------------------------------------- |
| `id`                      | string  | Response identifier from the AI provider |
| `model`                   | string  | Model ID that served the request         |
| `message`                 | string  | AI response content                      |
| `usage`                   | object  | Token usage statistics                   |
| `usage.prompt_tokens`     | number  | Input tokens consumed                    |
| `usage.completion_tokens` | number  | Output tokens generated                  |
| `usage.total_tokens`      | number  | Total tokens used                        |
| `done`                    | boolean | Always `true` (non-streaming)            |

### Error responses

| Status   | Error                                        | Description                                                                                                                                                                       |
| -------- | -------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 400      | `Message required`                           | The `message` field is missing from the request body                                                                                                                              |
| 429      | `Too many requests`                          | IP-based rate limit exceeded                                                                                                                                                      |
| 503      | `Demo unavailable — service not configured.` | The demo service is not configured on the server                                                                                                                                  |
| *varies* | `AI service error. Please try again.`        | The upstream AI provider returned an error. The HTTP status code is passed through from the provider (for example, `402` for quota issues or `422` for invalid model parameters). |
| 500      | `Failed to get response`                     | An unexpected error occurred                                                                                                                                                      |

<Note>The demo endpoint uses a fixed max token limit of 1024 and does not support streaming. For full chat capabilities, use the [AI chat endpoint](/api-reference/ai#chat-completion) with a subscription plan.</Note>

<Info>Every successful demo chat request automatically logs token usage and cost to the [usage tracking](/api-reference/usage-tracking) system. Demo requests are recorded with `userId: "demo"` and `agentId: "demo-chat"`, and are visible in the cost dashboard.</Info>

## Examples

### List models

```bash theme={"dark"}
curl https://agentbot.sh/api/demo/chat
```

### Send a message

```bash theme={"dark"}
curl -X POST https://agentbot.sh/api/demo/chat \
  -H "Content-Type: application/json" \
  -d '{
    "message": "What skills are available?",
    "model": "xiaomi/mimo-v2-pro"
  }'
```

### Send with conversation history

```bash theme={"dark"}
curl -X POST https://agentbot.sh/api/demo/chat \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Tell me more about that",
    "model": "openai/gpt-4o",
    "conversation": [
      { "role": "user", "content": "What is Agentbot?" }
    ]
  }'
```