Model Catalog

OfoxAI provides unified access to mainstream LLMs. You can browse all available models in the OfoxAI Model Catalog , or programmatically retrieve complete model information via the Models API.

Model Naming Convention

All models follow the provider/model-name format:


anthropic/claude-sonnet-4.5
google/gemini-3-flash-preview
moonshotai/kimi-k2.5

Models API Standard

OfoxAI’s Models API follows the OpenRouter standard, returning complete metadata for each model in JSON format.

API Response Structure

Root Response Object


{
  "object": "list",
  "data": [
    /* Array of Model objects */
  ]
}

Model Object

Each model contains the following standardized fields:

Field	Type	Description
`id`	string	Model identifier used in API requests, e.g. `"anthropic/claude-sonnet-4.5"`
`canonical_slug`	string	Permanent model identifier, never changes
`name`	string	Model display name
`created`	number	Time model was added (Unix timestamp)
`description`	string	Detailed description of model capabilities and features
`context_length`	number	Maximum context window size (tokens)
`architecture`	Architecture	Model technical architecture information
`pricing`	Pricing	Model pricing information
`top_provider`	TopProvider	Primary provider configuration
`supported_parameters`	string[]	List of supported API parameters

Architecture Object

Describes the model’s input/output modalities and tokenizer information:


{
  "modality": "text+image+file->text",
  "input_modalities": ["text", "image", "file"],
  "output_modalities": ["text"],
  "tokenizer": "claude",
  "instruct_type": null
}

Field	Description
`modality`	Shorthand for input/output modalities, e.g. `text+image->text`
`input_modalities`	Supported input types: `text`, `image`, `audio`, `file`
`output_modalities`	Supported output types: `text`
`tokenizer`	Tokenizer type
`instruct_type`	Instruction format type (`null` for some models)

Pricing Object

All prices are in USD per token. A value of "0" indicates free.


{
  "prompt": "0.000001",
  "completion": "0.000005",
  "input_cache_read": "0.0000001",
  "input_cache_write_5m": "0.00000125",
  "input_cache_write_1h": "0.000002"
}

Field	Description
`prompt`	Input token price
`completion`	Output token price
`input_cache_read`	Cache read token price
`input_cache_write_5m`	5-minute cache write token price
`input_cache_write_1h`	1-hour cache write token price

Different models use different tokenizers, so even with identical input and output text, the token count (and cost) may vary. Use the usage field in the response to get the actual token consumption.

TopProvider Object


{
  "context_length": 200000,
  "max_completion_tokens": 8192,
  "is_moderated": false
}

Field	Description
`context_length`	Provider-level context limit
`max_completion_tokens`	Maximum tokens per response
`is_moderated`	Whether content moderation is enabled

Supported Parameters

The supported_parameters array indicates which OpenAI-compatible parameters the model supports:

Parameter	Description
`temperature`	Sampling temperature control
`top_p`	Nucleus sampling parameter
`max_tokens`	Maximum response length
`stop`	Custom stop sequences
`tools`	Function Calling / Tool Use
`tool_choice`	Tool selection strategy
`response_format`	Output format specification (JSON Mode)
`reasoning`	Deep reasoning mode

Fetching the Model List

The Models API is a public endpoint that does not require an API Key.

cURL

Terminal


curl https://api.ofox.ai/v1/models

Python

models.py


import requests
 
resp = requests.get("https://api.ofox.ai/v1/models")
for model in resp.json()["data"]:
    print(f"{model['id']} — {model['name']}")

TypeScript

models.ts


const resp = await fetch('https://api.ofox.ai/v1/models')
const { data } = await resp.json()
 
for (const model of data) {
  console.log(`${model.id} — ${model.name}`)
}

For the complete live model list and pricing, visit the OfoxAI Model Catalog . For API endpoint details, see the Models API Reference.