> For the complete documentation index, see [llms.txt](https://docs.apismart.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apismart.ai/models-and-pricing/models-and-model-ids.md).

# Models and Model IDs

Learn how ApiSmart model IDs work, retrieve the latest model list, and choose supported text, image, and video models for your API requests.

ApiSmart provides access to text, image, and video models through a unified API.

Every generation request must include a valid `model` value. Model IDs are matched exactly, so always use the documented ID or retrieve the latest system model list before integrating a model.

### 🧩 Model IDs

The `model` parameter identifies which model should process your request.

For example:

```json
{
  "model": "deepseek-v4-flash"
}
```

Model IDs are **case-sensitive and format-sensitive**. Periods (`.`), hyphens (`-`), and version numbers must match exactly.

For example:

```
glm-5.1
gpt-5.6-luna
doubao-seedance-2-0-fast
doubao-seedream-5-0
```

Do not change:

```
glm-5.1
```

to:

```
glm-5-1
```

or:

```
doubao-seedance-2-0-fast
```

to:

```
doubao-seedance-2.0-fast
```

ApiSmart does not automatically correct or alias model IDs. An incorrectly written model ID may result in an unexpected `503`, so verify the model ID character by character when troubleshooting model-related requests.

### 🔍 Get the Latest Model List

To retrieve the current system model list, use:

**Method:** `GET`

**Endpoint:** `/v1/models`

Example:

```bash
curl https://gw.apismart.ai/v1/models \
  -H "Authorization: Bearer <your-api-key>"
```

The response uses an OpenAI-compatible list format:

```json
{
  "object": "list",
  "data": [
    {
      "id": "doubao-seedream-5-0",
      "object": "model",
      "owned_by": "api-gateway"
    },
    {
      "id": "deepseek-v4-flash",
      "object": "model",
      "owned_by": "api-gateway"
    }
  ]
}
```

Use:

```
data[].id
```

as the `model` value in supported API requests.

{% hint style="info" %}
**Model availability may change over time.**\
Use `GET /v1/models` when you need the latest system model list.
{% endhint %}

### 🔑 Model Availability and API Key Access

A model appearing in:

```
GET /v1/models
```

does **not necessarily mean that the model is enabled for your API Key**.

If the selected model exists but is not available to your account, the API may return:

```
403 model_not_allowed
```

In this case, choose a model available to your account or contact [**ApiSmart Support**](/help-and-resources/contact-support.md) if you need access.

### 💬 Text Models

Text models use the OpenAI-compatible:

```
POST /v1/chat/completions
```

endpoint.

The following text model IDs are documented in the current ApiSmart API specification:

| Model Family | Model IDs                |
| ------------ | ------------------------ |
| **DeepSeek** | `deepseek-v3.2`          |
|              | `deepseek-v4-flash`      |
|              | `deepseek-v4-pro`        |
| **GLM**      | `glm-5`                  |
|              | `glm-5.1`                |
|              | `glm-5.2`                |
|              | `glm-5-turbo`            |
| **GPT**      | `gpt-5.4`                |
|              | `gpt-5.4-mini`           |
|              | `gpt-5.4-nano`           |
|              | `gpt-5.6-luna`           |
|              | `gpt-5.6-sol`            |
|              | `gpt-5.6-terra`          |
| **Kimi**     | `kimi-k2.5`              |
|              | `kimi-k2.6`              |
|              | `kimi-k2.7-code`         |
|              | `kimi-k3`                |
| **MiniMax**  | `minimax-m2.5`           |
|              | `minimax-m2.5-highspeed` |
|              | `minimax-m2.7`           |
|              | `minimax-m3`             |
| **Qwen**     | `qwen3.5-397b-a17b`      |
|              | `qwen3.6-plus`           |
|              | `qwen3.7-max`            |

These IDs come from the current API specification. Use `GET /v1/models` when you need to verify the latest system list.

For request examples and streaming behavior, see [**Chat Completions API**](/api-guides/chat-completions-api.md).

### 🖼️ Image Models

The current image generation model is:

| Model            | Model ID              |
| ---------------- | --------------------- |
| **Seedream 5.0** | `doubao-seedream-5-0` |

Use it with:

```
POST /v1/images/generations
```

For local image uploads and edits, use the image editing workflow documented in [**Image Generation API**](/api-guides/image-generation-api.md).

The current API specification identifies `doubao-seedream-5-0` as the image generation model.

### 🎬 Video Models

Video generation uses asynchronous tasks through:

```
POST /v1/video/tasks
```

After creating a task, query its status with:

```
GET /v1/video/tasks/{id}
```

Video generation currently includes HappyHorse and Seedance model families.

#### HappyHorse

| Model              | Model ID         |
| ------------------ | ---------------- |
| **HappyHorse 1.0** | `happyhorse-1.0` |
| **HappyHorse 1.1** | `happyhorse-1.1` |

HappyHorse supports multiple video generation workflows, including video editing where supported.

#### Seedance

| Model                 | Model ID                   |
| --------------------- | -------------------------- |
| **Seedance 2.0**      | `doubao-seedance-2.0`      |
| **Seedance 2.0 Fast** | `doubao-seedance-2-0-fast` |
| **Seedance 2.0 Mini** | `doubao-seedance-2-0-mini` |
| **Seedance 2.5**      | `doubao-seedance-2-5`      |

Supported resolutions, inputs, workflows, and billing differ by video model.

For those details, see [**Video Generation API**](/api-guides/video-generation-api.md) and [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md).

### 🔀 Model and Endpoint Compatibility

Use the correct model type with the correct API endpoint:

| Workload         | Endpoint                      | Model Type             |
| ---------------- | ----------------------------- | ---------------------- |
| Text generation  | `POST /v1/chat/completions`   | Text models            |
| Image generation | `POST /v1/images/generations` | Image models           |
| Image editing    | `POST /v1/images/edits`       | Supported image models |
| Video generation | `POST /v1/video/tasks`        | Video models           |

A valid Model ID can still fail if it is used with an incompatible endpoint.

For example:

```
403 model_not_image_capable
```

means the selected model cannot be used with the Image Generation API.

```
403 model_not_video_capable
```

means the selected model cannot be used with the Video Generation API.

### ⚠️ Common Model Errors

| Error                         | Meaning                                 | What to Check                        |
| ----------------------------- | --------------------------------------- | ------------------------------------ |
| `403 model_not_allowed`       | Model is not available to your API Key  | Model access                         |
| `403 model_not_image_capable` | Model does not support image generation | Model and endpoint                   |
| `403 model_not_video_capable` | Model does not support video generation | Model and endpoint                   |
| `503` after changing a model  | Model ID may be incorrect               | Periods, hyphens, and version number |

If you encounter an unexpected model error, first retrieve the model list and compare the ID exactly:

```bash
curl https://gw.apismart.ai/v1/models \
  -H "Authorization: Bearer <your-api-key>"
```

For further troubleshooting, see [**Model and Request Errors**](/troubleshooting/model-and-request-errors.md) or [**HTTP Status Codes and API Errors**](/troubleshooting/http-status-codes-and-api-errors.md).

### 💰 Model Pricing

Model prices and billing methods vary by workload and model.

For example, text, image, and video models do not necessarily use the same billing method.

To keep model selection separate from pricing rules, this page does not duplicate individual model prices.

See [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md) for current billing information.

### ✅ Before Using a Model

Before sending a request, verify that the Model ID appears exactly as documented or returned by `GET /v1/models`, that the model is compatible with your selected endpoint, and that your API Key has access to it.

When integrating a model into a production application, avoid assuming that the system model list will remain unchanged indefinitely.

### ➡️ Next Steps

* [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md) — Understand model-specific pricing
* [**Chat Completions API**](/api-guides/chat-completions-api.md) — Use text models
* [**Image Generation API**](/api-guides/image-generation-api.md) — Use image models
* [**Video Generation API**](/api-guides/video-generation-api.md) — Use video models
* [**Model and Request Errors**](/troubleshooting/model-and-request-errors.md) — Troubleshoot model and request failures