Ship AI features, not assembly.
Connect to 104 models with one OpenGateway API key and base URL. Use supported APIs, explore UltraFast and Decisions, and manage usage and billing in one console.
OpenGateway gives you one API key and base URL for models in a shared catalog. Choose a model by its creator-prefixed ID, send requests through a supported API, and review activity in the console.
The catalog currently lists 104 models. Creator namespaces include openai/, anthropic/, google/, x-ai/, moonshotai/, deepseek/, z-ai/, qwen/, minimax/, sionic-ai/, and typesafe/. Keys can be limited to selected models by your team.
Get started#
- What is OpenGateway? — Learn how the gateway, model catalog, and console fit together.
- Quickstart — Create a key and make a request with curl or the OpenAI SDK.
- Migrate from OpenAI — Change the base URL, key, and model ID in an existing Chat Completions integration.
Explore the platform#
- Models and routing — Find model IDs and understand how requests are routed.
- UltraFast — Review UltraFast model behavior and current pricing guidance.
- Decisions API — Evaluate structured input with classification, choice, or scoring questions.
- Usage and logs — Inspect request activity and usage in the console.
- Billing — Manage credits and review payment information.
Coding-agent guides#
Use a separate OpenGateway option in the coding agent you use:
Product operations#
API requests use a model ID and an endpoint supported by that model. Check the catalog for available IDs and endpoint support; see the API reference for the base URL, authentication, and endpoint list.