> For the complete documentation index, see [llms.txt](https://docs.nebulablock.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nebulablock.com/api-reference/inference-api/list-models.md).

# List Models

List the models available on Nebula Block, either OpenAI-style or with full catalog metadata and per-tier limits.

Two endpoints return the model catalog: an OpenAI-compatible one that lists model IDs, and a richer one that adds context lengths, pricing, and per-tier limits.

## OpenAI-compatible list

Use this when you want the same response shape an OpenAI client expects — for example to populate a model picker through an SDK.

### HTTP Request

`GET` `https://inference.nebulablock.com/v1/models`

### Response Attributes

#### object `string`

Always `list`.

#### data `list`

The available models. Each entry contains:

* **id** `string`: The model ID. This is the value you pass as `model` in an inference request.
* **object** `string`: Always `model`.
* **created** `integer`: Unix timestamp of when the model was added.
* **owned\_by** `string`: The model's provider.

### Example

#### Request

```bash
curl -X GET 'https://inference.nebulablock.com/v1/models' \
-H 'Authorization: Bearer {TOKEN/KEY}'
```

#### Response

```json
{
    "object": "list",
    "data": [
        {
            "id": "gemini/gemini-3.7-flash",
            "object": "model",
            "created": 1786647688,
            "owned_by": "google"
        },
        {
            "id": "deepseek-ai/DeepSeek-V3.2",
            "object": "model",
            "created": 1785780016,
            "owned_by": "deepseek-ai"
        }
    ]
}
```

## Full catalog

Use this when you need more than the ID — context length, pricing, or the per-tier daily limits that apply to a model.

### HTTP Request

`GET` `https://api.nebulablock.com/api/v1/serverless/models`

### Response Attributes

#### data `dict`

Contains `models`, a list of model objects. Each has:

* **model\_name** `string`: The unique model ID. Pass this as `model` in inference calls.
* **model\_alias** `string`: The human-readable display name.
* **model\_type** `string`: `Text`, `multimodal`, `Vision`, `Image`, `Video`, `Embedding`, or `Rerank`.
* **context\_length** `integer`: Context window in tokens, or `null` for media models.
* **max\_completion\_tokens** `integer`: Maximum tokens the model will generate, where applicable.
* **description** `string`: A short description of the model.
* **input\_price** / **output\_price** `float`: List price. The unit depends on the model type — per 1M tokens for text and multimodal models, per image or per second for media models. Promotional rates are applied on top and are not reflected here; see the [pricing page](https://www.nebulablock.com/pricing/serverless-ai).
* **cache\_read\_input\_price** / **cache\_creation\_input\_price** `float`: Prompt-caching rates, where the model supports caching.
* **hosting\_in** `string`: Where the model is hosted. `CA` marks Canadian-hosted models.
* **parameter\_size** `string`: Parameter count, for open-weight models.
* **huggingface\_url** `string`: The model's Hugging Face page, where applicable.
* **restrictions** `dict`: The daily request cap per tier — `RPD_ENGINEER_TIER_1` through `RPD_EXPERT_TIER_1`. A value of `0` means the model cannot be called on that tier. See [Tiers and Rate Limits](/account/tiers-and-limits.md).
* **tags** `dict`: `modality`, `use_case`, `highlight`, and `model_family` labels.

#### status `string`

`success` or `failed`.

#### message `string`

A description of the result.

### Example

#### Request

```bash
curl -X GET 'https://api.nebulablock.com/api/v1/serverless/models' \
-H 'Content-Type: application/json'
```

#### Response

```json
{
    "data": {
        "models": [
            {
                "model_name": "gemini/gemini-3.7-flash",
                "model_alias": "Gemini-3.7-Flash",
                "model_type": "multimodal",
                "context_length": 1048576,
                "max_completion_tokens": 65536,
                "description": "Google's newest Flash model — stronger multimodal reasoning, coding and agentic performance at Flash speed",
                "input_price": 1.5,
                "output_price": 7.5,
                "cache_read_input_price": 0.075,
                "cache_creation_input_price": null,
                "hosting_in": "-",
                "parameter_size": "-",
                "huggingface_url": "",
                "restrictions": {
                    "restriction_type": "model_name",
                    "restriction_name": "gemini/gemini-3.7-flash",
                    "RPD_ENGINEER_TIER_1": 0,
                    "RPD_ENGINEER_TIER_2": 5000,
                    "RPD_ENGINEER_TIER_3": 10000,
                    "RPD_EXPERT_TIER_1": 50000
                },
                "tags": {
                    "modality": ["multimodal", "text_generation"],
                    "use_case": [],
                    "highlight": ["recently_added", "featured"],
                    "model_family": ["Gemini"]
                }
            }
        ]
    },
    "message": "Get models list successfully.",
    "status": "success"
}
```

## See also

* [Model Catalog](/products/serverless-inference/model-catalog.md)
* [Tiers and Rate Limits](/account/tiers-and-limits.md)
* [Chat Completions](/api-reference/inference-api/chat-completions.md)