Available Models - OneFirewall Documentation

The Secure AI Gateway provides a unified interface to multiple AI models. Specify the model with the model parameter in your API requests.

Model ID	Provider	Description
`openai/gpt-4o-mini`	OpenAI	Fast and cost-effective for simple tasks
`openai/gpt-4o`	OpenAI	Most capable OpenAI model
`openai/gpt-5.2`	OpenAI	The best model for coding and agentic tasks
`google/gemini-2.5-flash`	Google	Fastest and most cost-efficient multimodal model
`google/gemini-2.5-pro`	Google	Most capable Google model with advanced reasoning
`xai/grok-4-1-fast-reasoning`	xAI / Reasoning	Fast reasoning and problem solving
`deepseek/deepseek-reasoner`	DeepSeek	Advanced reasoning model
`deepseek/deepseek-chat`	DeepSeek	Fast and efficient chat model (V3)
`openai/o1`	OpenAI	Advanced reasoning and problem-solving
`minimax/MiniMax-M2.1`	MiniMax	Reasoning model with tool support

Model Selection

To use a specific model, pass its ID in the request body:

{
  "model": "deepseek/deepseek-reasoner",
  "messages": [...]
}

Feature	Support
Text Generation	All models
Visual Input (Vision)	`openai/gpt-4o`, `openai/gpt-5.2`, `google/gemini-2.5-pro`, `xai/grok-4-1-fast-reasoning`
Web Search	All models (via Gateway tool)
Streaming	All models

The gateway follows the OpenAI API structure, so standard clients can fetch available models dynamically.

Retrieves the list of currently supported models in the standard OpenAI response format. Example Request:

curl http://localhost:3000/api/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY_HERE"

Retrieves information about a specific model. Model IDs with slashes (e.g. openai/gpt-4o) are fully supported. Example Request:

curl http://localhost:3000/api/v1/models/openai/gpt-4o \
  -H "Authorization: Bearer YOUR_API_KEY_HERE"