Back to directory

New API

New API is a self-hosted AI gateway that lets a team connect upstream model services once and expose a consistent, cross-converted OpenAI-, Claude- or Gemini-compatible API to its own clients and agents.

New API

It manages routing, access, usage and cost from one web console, covering model mappings, channel priorities and weights, retries and channel affinity, quotas, usage logs, expression-based pricing, OAuth/OIDC and passkey login, two-factor authentication, and JavaScript-pluggable asynchronous image and video task handling. Supported upstreams include OpenAI, Anthropic, Google Gemini, Azure OpenAI, AWS Bedrock, Vertex AI, DeepSeek and Qwen, with endpoints mirroring OpenAI chat and responses, Anthropic messages, and Gemini's generate-content interface, plus realtime and image and audio endpoints.

The project states it is intended only for lawful, authorized gateway use, and asks operators of any public-facing deployment to meet their own jurisdiction's filing, licensing, content-safety and log-retention obligations.

Go, AGPL-3.0 licensed.

More in LLM gateways

See all 106
  • aihappey-ai

    github.com

    A stateless, multi-provider .NET AI gateway exposing normalized OpenAI- and Anthropic-compatible endpoints, managed agents and skills across a very large catalog of models.

  • Unified AI System

    happy520ai.github.io

    A self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A, turning a rough request into a structured, reviewable prompt before it runs.

  • Subroute

    github.com

    A local AI gateway and desktop control desk that gives coding tools one steady endpoint, so switching between AI subscriptions, API providers and local models doesn't mean reconfiguring every client.