What is OpenGateway?

OpenGateway provides a shared API surface for models in its catalog. Choose a model by its creator-prefixed ID, send requests to an endpoint supported by that model, then review activity in the console.

Overview#

Use one OpenGateway API key and base URL for catalog models that your key is allowed to access. The gateway accepts supported API formats and routes each request to an available provider for the selected model. Model and endpoint availability are listed in the catalog.

Catalog and model IDs#

The catalog currently lists 104 models. Model IDs use the creator/model pattern. Creator namespaces include openai/, anthropic/, google/, x-ai/, moonshotai/, deepseek/, z-ai/, qwen/, minimax/, sionic-ai/, and typesafe/.

For example, current IDs include openai/gpt-5-mini, anthropic/claude-sonnet-4-6, google/gemini-2.5-flash, and x-ai/grok-4.7. Check Models or the public GET /v1/models endpoint for current IDs and endpoint support. API keys can be restricted to selected models.

APIs#

The data plane includes Chat Completions, Responses, Anthropic Messages, embeddings, image generation and editing, and Decisions. A model can be used only with endpoints listed for it in the catalog. For the full route list, see the API reference.

OpenGateway also offers UltraFast models and a Decisions API for structured evaluation. Their capabilities and eligible models differ from text generation APIs.

Console#

Create and manage keys in the dashboard, browse the model catalog, and review request activity in usage and logs. See billing for credits and payment details.