List models
Reference for GET /v1/models, which lists the available models with their capabilities and prices.
This page is the reference for the models endpoint of the Inference API. It is intended for developers who select models or display prices in their applications.
Endpoint
GET https://api.engy.ai/v1/modelsAuthentication
Authentication is optional. If you send a valid API key in the Authorization header, the prices reflect any pricing that applies to your account. Without a key, the endpoint returns list prices.
Parameters
This endpoint takes no parameters.
Response
Response fields
| Field | Type | Description |
|---|---|---|
object | String | Always list. |
data | Array | The model objects. |
data[].id | String | The model ID to use in requests. |
data[].object | String | Always model. |
data[].created | Integer | The time of the response, as a Unix timestamp in seconds. |
data[].owned_by | String | Always engy. |
data[].input_modalities | Array | The input types that the model accepts, such as text and image. |
data[].output_modalities | Array | The output types. Always ["text"]. |
data[].context_length | Integer | The maximum number of tokens in the context window. |
data[].max_model_len | Integer | The same value as context_length. |
data[].pricing.prompt | String | The price per input token, in USD. |
data[].pricing.completion | String | The price per output token, in USD. |
data[].pricing.input_cache_read | String | The price per cached input token, in USD. Absent if the model has no cached rate. |
data[].pricing.request | String | The price per request, in USD. Always "0". |
data[].pricing.image | String | The price per image, in USD. Always "0". |
data[].x_engy.price_source | String | Present only if the prices are specific to your account. |
Model aliases, such as deepseek-v4.1-flash-1017, appear as separate entries with the same values as the model they refer to.
Errors
This endpoint does not return endpoint-specific errors. An invalid API key does not cause an error. The endpoint returns list prices instead.
Example
curl https://api.engy.ai/v1/modelsResponse:
{
"object": "list",
"data": [
{
"id": "glm-5.2",
"object": "model",
"created": 1792281600,
"owned_by": "engy",
"input_modalities": ["text"],
"output_modalities": ["text"],
"context_length": 262144,
"max_model_len": 262144,
"pricing": {
"prompt": "0.00000068",
"completion": "0.0000015",
"request": "0",
"image": "0",
"input_cache_read": "0.00000018"
}
}
]
}