Base
Hardened build
minimal ports, security patches applied at build time
New API
Azure
Artificial Intelligence (AI)
1 variation
A self hosted AI gateway that puts many model providers behind one OpenAI compatible API, with keys, quotas and usage logs
Variations
This product is available in the build below. Open it for the operating system, cloud and version detail, or read its deployment guide.
Overview
New API is an open source AI gateway for applications, agents and teams. You connect upstream model services as channels, such as OpenAI, Anthropic, Google Gemini, Azure OpenAI, AWS Bedrock, DeepSeek or any OpenAI compatible endpoint, and New API exposes them to your clients through one consistent API. It routes each request to a channel that serves the requested model, converts between provider formats where needed, and streams the response back. A web console manages channels, models and their prices, users and groups, per client API keys with quotas and expiry, and records every call with its tokens, cost and latency so you can see who used what. Data lives in an embedded SQLite database, so a single virtual machine runs the whole gateway. It suits teams who want one audited entry point to many model providers, and developers who want to switch providers without reconfiguring every client.
Why the cloudimg image
Out of the box the upstream release lets whoever reaches it first create the administrator through its setup wizard, and it leaves open self registration switched on. cloudimg closes both before the gateway is reachable: first boot completes setup on loopback with an administrator password generated for that virtual machine, turns registration off, and proves the password works, a wrong one is refused and the wizard is closed before nginx is allowed to start. The console and API are served over HTTPS with a certificate generated per virtual machine, the application port is fenced to loopback so nginx is the only way in, and the session and encryption secrets are unique to each deployment. The official release binary is pinned by checksum and shipped unmodified with its licence and notices, and every deployment is fully patched with a paired deploy guide and 24/7 cloudimg support.
Common uses
- Give a team one OpenAI compatible endpoint in front of several model providers
- Issue per application API keys with quotas and expiry, and see usage and cost per key
- Switch or fail over between providers without changing client configuration
More in Artificial Intelligence (AI)
Argilla
Artificial Intelligence (AI)
Argilla, an open source data annotation and curation platform for building high quality datasets for natural language pr
Bifrost
Artificial Intelligence (AI)
one OpenAI compatible endpoint in front of every model provider, packaged by cloudimg
ContextForge MCP Gateway
Artificial Intelligence (AI)
ContextForge, the open source model context protocol gateway from IBM: federate many MCP servers behind one authenticate
Crawl4AI
Artificial Intelligence (AI)
an open source web crawler that turns any web page into clean, LLM ready markdown over a REST API, secured from first bo
Do
DeepWiki-Open
Artificial Intelligence (AI)
turn any Git repository into a browsable, AI generated wiki
Dify
Artificial Intelligence (AI)
Dify, a source available platform for building LLM apps, agents, RAG and workflows from a visual console.