Model Management API

This API documentation provides a detailed description of the model management interface, including the features, request examples, parameter descriptions, and response formats for both the new and legacy API versions.

GET https://aihubmix.com/api/v1/models

Model Management API

cURL

curl --request GET \
  --url https://aihubmix.com/api/v1/models \
  --header 'Authorization: Bearer <token>'

200

{
  "data": [
    {}
  ],
  "model_id": "<string>",
  "desc": "<string>",
  "types": "<string>",
  "features": "<string>",
  "input_modalities": "<string>",
  "max_output": "<string>",
  "context_length": "<string>",
  "pricing": {},
  "pricing.input": 123,
  "pricing.output": 123,
  "pricing.cache_read": 123,
  "pricing.cache_write": 123
}

New API Version

Get Model Information

Endpoint: GET https://aihubmix.com/api/v1/models

Description: Fetches detailed information for all available models.

Model Object Field Descriptions

data · array

An array of model information objects.

model_id · string

The unique identifier for the model.

desc · string

A description of the model’s functionality (in English).

types · string

Model type. Supported values: llm (Large Language Model), image_generation, video, tts (Text-to-Speech), stt (Speech-to-Text), embedding, rerank.

features · string

Supported features. Supported values: thinking (reasoning), tools (tool use), function_calling, web (web search), deepsearch, long_context, structured_outputs.

input_modalities · string

Supported input modalities. Supported values: text, image, audio, video, pdf.

max_output · string

Maximum number of output tokens.

context_length · string

Context window size (maximum number of input tokens).

pricing · object

Pricing information object.

pricing.input · number

Input token price (per 1K tokens, in USD).

pricing.output · number

Output token price (per 1K tokens, in USD).

pricing.cache_read · number

Cache read price (per 1K tokens, in USD, optional field).

pricing.cache_write · number

Cache write price (per 1K tokens, in USD, optional field).

Request Examples

Python

import requests

# API Endpoint
url = "https://aihubmix.com/api/v1/models"

response = requests.get(url)
print(response.json())

# Example with parameters
params = {
    "type": "llm",                   
	"modalities": "text",
	"model": "gpt-5",
	"features": "thinking",
    "sort_by": "context_length",
    "sort_order": "desc"    
}
response = requests.get(url, params=params)
print(response.json())

Request Parameter Descriptions (for Filtering)

type · string

Model type. Supported values: llm (Large Language Model), image_generation, video, tts (Text-to-Speech), stt (Speech-to-Text), embedding, rerank.

modalities · string

Input modalities. Supported values: text, image, audio, video, pdf. Supports multi-modality queries (comma-separated).

model · string

Fuzzy search for model name (supports partial matching).

features · string

Model features. Supported values: thinking (reasoning), tools (tool use), function_calling, web (web search), deepsearch, long_context, structured_outputs. Supports multi-feature queries (comma-separated).

sort_by · string

Sort by field. Supported values:

• model_ratio: Sort by cost-effectiveness.
• context_length: Sort by context length.
• coding: Prioritize coding models.
• order: Sort by default order.

sort_order · string

Sort order. Supported values:

• asc (ascending)
• desc (descending)

Successful Response Example

{
    "data": [
        {
            "model_id": "gpt-5",
            "desc": "GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.",
            "pricing": {
                "cache_read": 0.125,
                "input": 1.25,
                "output": 10
            },
            "types": "llm",
            "features": "thinking,tools,function_calling,structured_outputs",
            "input_modalities": "text,image",
            "max_output": 128000,
            "context_length": 400000
        },
        {
            "model_id": "gpt-5-codex",
            "desc": "GPT-5-Codex is a version of GPT-5 optimized for autonomous coding tasks in Codex or similar environments. It is only available in the Responses API, and the underlying model snapshots will be updated regularly. https://docs.aihubmix.com/en/api/Responses-API You can also use it in codex-cll; see https://docs.aihubmix.com/en/api/Codex-CLI for using codex-cll through Aihubmix.",
            "pricing": {
                "cache_read": 0.125,
                "input": 1.25,
                "output": 10
            },
            "types": "llm",
            "features": "thinking,tools,function_calling,structured_outputs",
            "input_modalities": "text,image",
            "max_output": 128000,
            "context_length": 400000
        }
    ],
    "message": "",
    "success": true
}

Usage Scenario Examples

Get all large language models

GET https://aihubmix.com/api/v1/models?type=llm

Note: When using smart sort for coding models, the system will prioritize models tagged with coding, and other models will be listed in the default order.

Performance Optimization

Caching Mechanism

• Cache Policy: HTTP caching, cache duration 300 seconds (5 minutes).
• Cache Control: Cache-Control: public, max-age=300, stale-while-revalidate=300
• Content Validation: Supports ETag content hash validation.

Cache Usage Example

# Conditional request using ETag
curl -H "If-None-Match: \"abc123...\"" \
     https://aihubmix.com/api/v1/models

If the content has not been updated, the server returns a 304 Not Modified status code.

Error Handling

400 Bad Request (Invalid Parameters)

{
  "success": false,
  "message": "Invalid request parameter format"
}

Important Notes

1. Data Integrity: This endpoint returns all models that meet the criteria, without pagination.
2. Type Compatibility: Supports automatic mapping between new and old type identifiers:
   • t2t ↔ llm
   • t2i ↔ image_generation
   • t2v ↔ video
   • reranking ↔ rerank
3. Filtering Logic: Multiple filter conditions are combined with a logical AND.
4. Sorting Rule: When no sorting method is specified, models are arranged in the system’s default order.

---

Legacy API Version

⚠️ Note: The following are legacy API endpoints. It is recommended to use the new API version for better performance and features.

Get Model List

Endpoint: GET /v1/models

• If a user is logged in, it retrieves the list of available models for the user’s group. If no user is logged in, it retrieves the list for the default group.
• If the header contains an Authorization field, it queries the list of models configured for the corresponding token.

Response Example:

{
  "data": [
    {
      "id": "gpt-4o-mini",
      "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": "gpt-4o-mini",
      "parent": null
    }
  ]
}

Response

Status Code	Meaning	Description	Data Model
200	OK	none	Inline

Response Data Structure

Status Code 200

Name	Type	Required	Description
» data	[object]	true	none
»» id	string	true	Model ID
»» object	string	true	model
»» created	integer	true	Timestamp of creation
»» owned_by	string	true	Developer
»» permission	[object]¦null	true	none
»»» id	string	true	none
»»» object	string	true	none
»»» created	integer	true	none
»»» allow_create_engine	boolean	true	none
»»» allow_sampling	boolean	true	none
»»» allow_logprobs	boolean	true	none
»»» allow_search_indices	boolean	true	none
»»» allow_view	boolean	true	none
»»» allow_fine_tuning	boolean	true	none
»»» organization	string	true	none
»»» group	null	true	none
»»» is_blocking	boolean	true	none
»» root	string	true	Root model name
»» parent	null	true	Parent model

Get Model Information

Endpoint: GET /v1/models/:model

Request Parameters

Name	In	Type	Required	Description
model	path	string	true	Model ID

Response Example:

200 Response

{
  "id": "string",
  "object": "string",
  "created": 0,
  "owned_by": "string",
  "permission": [
    {
      "id": "string",
      "object": "string",
      "created": 0,
      "allow_create_engine": true,
      "allow_sampling": true,
      "allow_logprobs": true,
      "allow_search_indices": true,
      "allow_view": true,
      "allow_fine_tuning": true,
      "organization": "string",
      "group": null,
      "is_blocking": true
    }
  ],
  "root": "string",
  "parent": null
}

Response

Status Code	Meaning	Description	Data Model
200	OK	none	Inline

Response Data Structure

Status Code 200

Name	Type	Required	Description
id	string	true	Model ID
object	string	true	model
created	integer	true	Timestamp of creation
owned_by	string	true	Developer
permission	[object]	true	none
» id	string	false	none
» object	string	false	none
» created	integer	false	none
» allow_create_engine	boolean	false	none
» allow_sampling	boolean	false	none
» allow_logprobs	boolean	false	none
» allow_search_indices	boolean	false	none
» allow_view	boolean	false	none
» allow_fine_tuning	boolean	false	none
» organization	string	false	none
» group	null	false	none
» is_blocking	boolean	false	none
root	string	true	Root model name
parent	null	true	Parent model

---

Last updated: 2026-06-01