List Models
Retrieve a list of available models from the Unbound gateway.
Endpoint
| Header | Type | Required | Description |
|---|
Authorization | string | No | Bearer token with your API key. Optional — the endpoint returns the public model catalog without authentication. Pass your key to receive your organization’s filtered model list. |
Example Request
curl -X GET 'https://api.getunbound.ai/v1/models' \
-H "Authorization: Bearer YOUR_API_KEY"
Example Response
{
"object": "list",
"data": [
{
"id": "anthropic/claude-sonnet-4-20250514",
"created": 1777913942,
"pricing": {
"input_token_price": "3.000000",
"output_token_price": "15.000000",
"cache_read_price": "0.300000",
"cache_write_price": "3.750000"
},
"parameters": {
"context_window": 200000,
"max_tokens": 8192,
"supports_prompt_caching": true,
"supports_computer_use": true,
"supports_images": true
}
},
{
"id": "openai/gpt-4o",
"created": 1777913942,
"pricing": {
"input_token_price": "2.500000",
"output_token_price": "10.000000",
"cache_read_price": "1.250000",
"cache_write_price": "0.000000"
},
"parameters": {
"context_window": 128000,
"max_tokens": 16384,
"supports_prompt_caching": false,
"supports_computer_use": false,
"supports_images": true
}
}
]
}
Response Fields
| Field | Type | Description |
|---|
object | string | Always "list" |
data | array | Array of model objects |
data[].id | string | Model identifier in provider/model-name format |
data[].created | integer | Unix timestamp |
data[].pricing.input_token_price | string | Price per million input tokens (USD) |
data[].pricing.output_token_price | string | Price per million output tokens (USD) |
data[].pricing.cache_read_price | string | Price per million cache-read tokens (USD) |
data[].pricing.cache_write_price | string | Price per million cache-write tokens (USD) |
data[].parameters.context_window | integer | Maximum context window in tokens |
data[].parameters.max_tokens | integer | Maximum output tokens |
data[].parameters.supports_images | boolean | Whether the model accepts image inputs |
data[].parameters.supports_prompt_caching | boolean | Whether the model supports prompt caching |
data[].parameters.supports_computer_use | boolean | Whether the model supports computer use tools |
Model availability depends on your organization’s configuration and routing rules. Use the /v1/models endpoint to get the current list of available models.
