API reference
List models
Reference for GET /api/v1/models, which returns the model catalog with prices and token limits.
This page is the reference for the models endpoint of the Management API. It is intended for developers who need model prices and token limits in micro-USD.
To list models without an account token, use the Inference API endpoint GET /v1/models instead.
Endpoint
GET https://engy.ai/api/v1/modelsAuthentication
Send your account token in the Authorization header as a bearer token. For details, see Management API overview.
Parameters
This endpoint takes no parameters.
Response
Response fields
| Field | Type | Description |
|---|---|---|
data[].model | String | The model ID. |
data[].input_per_1k_micro | Integer | The price per 1,000 input tokens, in micro-USD. |
data[].output_per_1k_micro | Integer | The price per 1,000 output tokens, in micro-USD. |
data[].cached_per_1k_micro | Integer or null | The price per 1,000 cached input tokens, in micro-USD. null if the model has no cached rate. |
data[].input_per_1k_usd | String | The price per 1,000 input tokens, in USD. |
data[].output_per_1k_usd | String | The price per 1,000 output tokens, in USD. |
data[].max_input_tokens | Integer | The maximum number of input tokens. |
data[].max_output_tokens | Integer | The maximum number of output tokens. |
meta.count | Integer | The number of models. |
The context window that the Inference API reports in context_length is the sum of max_input_tokens and max_output_tokens.
Errors
This endpoint returns the common errors only. For details, see Management API overview.
Example
curl https://engy.ai/api/v1/models \
-H "Authorization: Bearer $ENGY_ACCOUNT_TOKEN"Response:
{
"data": [
{
"model": "glm-5.2",
"input_per_1k_micro": 680,
"output_per_1k_micro": 1500,
"cached_per_1k_micro": 180,
"input_per_1k_usd": "0.00068",
"output_per_1k_usd": "0.0015",
"max_input_tokens": 196608,
"max_output_tokens": 65536
}
],
"meta": {
"count": 1
}
}