List Available Models
GEThttps://knox.chat/v1/models
Returns a list of models available through the API
Request
This endpoint does not require any request parameters.
Request Headers
Name | Type | Required | Description |
---|---|---|---|
Authorization | String | Yes | Bearer authentication in the format Bearer <token>, where token is your authentication token. |
cURL Example
curl -X GET https://knox.chat/v1/models \
-H "Authorization: Bearer <token>" \
-H "Content-Type: application/json"
Response
Success Response (200)
{
"data": [
{
"id": "anthropic/claude-sonnet-4",
"object": "model",
"created": 1626777600,
"owned_by": "openai",
"permission": [
{
"id": "modelperm-LwHkVFn8AcMItP432fKKDIKJ",
"object": "model_permission",
"created": 1626777600,
"allow_create_engine": true,
"allow_sampling": true,
"allow_logprobs": true,
"allow_search_indices": false,
"allow_view": true,
"allow_fine_tuning": false,
"organization": "*",
"group": null,
"is_blocking": false
}
],
"root": "anthropic/claude-sonnet-4",
"parent": null,
"context_length": 200000,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
"image",
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Claude"
},
"pricing": {
"prompt": "0.000003",
"completion": "0.000015",
"request": "0",
"image": "0.0048",
"audio": "0",
"web_search": "0",
"internal_reasoning": "0",
"input_cache_read": "0.0000003",
"input_cache_write": "0.00000375"
},
"top_provider": {
"context_length": 200000,
"max_completion_tokens": 64000
},
"supported_parameters": [
"max_tokens",
"temperature",
"stop",
"reasoning",
"include_reasoning",
"tools",
"tool_choice",
"top_p",
"top_k"
]
},
more...
]
}
Response Schema
Name | Type | Description |
---|---|---|
data | array | Array of available models |
data[].id | string | Unique identifier for the model |
data[].object | string | Object type, fixed as "model" |
data[].created | integer | Unix timestamp of when the model was created |
data[].owned_by | string | Owner of the model |
data[].permission | array | Array of model permissions |
data[].permission[].id | string | Permission ID |
data[].permission[].object | string | Object type |
data[].permission[].created | integer | Timestamp when the permission was created |
data[].permission[].allow_create_engine | boolean | Whether engine creation is allowed |
data[].permission[].allow_sampling | boolean | Whether sampling is allowed |
data[].permission[].allow_logprobs | boolean | Whether log probabilities are allowed |
data[].permission[].allow_search_indices | boolean | Whether search indices are allowed |
data[].permission[].allow_view | boolean | Whether viewing is allowed |
data[].permission[].allow_fine_tuning | boolean | Whether fine-tuning is allowed |
data[].permission[].organization | string | Organization information |
data[].permission[].group | null or string | Group information |
data[].permission[].is_blocking | boolean | Whether the permission is blocking |
data[].root | string | Root model ID |
data[].parent | null or string | Parent model ID |
data[].context_length | integer | Maximum context length of the model |
data[].architecture | object | Information about the model's architecture |
data[].architecture.modality | string | Modality mapping from input to output (e.g., "text+image->text") |
data[].architecture.input_modalities | array of strings | Supported input modalities (e.g., "text", "image") |
data[].architecture.output_modalities | array of strings | Supported output modalities (e.g., "text") |
data[].architecture.tokenizer | string | Type of tokenizer used |
data[].pricing | object | Pricing information for model usage |
data[].pricing.prompt | string | Price per prompt token |
data[].pricing.completion | string | Price per completion token |
data[].pricing.request | string | Base cost per request |
data[].pricing.image | string | Cost per image processed |
data[].pricing.audio | string | Audio processing cost |
data[].pricing.web_search | string | Web search cost |
data[].pricing.internal_reasoning | string | Internal reasoning cost |
data[].pricing.input_cache_read | string | Input cache read cost |
data[].pricing.input_cache_write | string | Input cache write cost |
data[].top_provider | object | Information about the top provider |
data[].top_provider.context_length | integer | Context length provided by the top provider |
data[].top_provider.max_completion_tokens | integer | Maximum number of completion tokens |
data[].supported_parameters | array of strings | List of supported parameters |