One API gateway details

An open-source project for managing and distributing OpenAI-style interfaces; commonly used to self-host an API relay with channel management, quotas, and token grouping.

Best for: For webmasters, internal team gateways, and scenarios needing multi-channel key management and quota allocation.

Current status

Self-hosted

Latency reference

Depends on your deployment

/models check

Self-hosted configuration

Last verified

2026-07-01

Status notes

An open-source channel-management project, suited to internal team or webmaster self-hosting.

Pricing mode

Open-source and self-hosted; you bear channel and deployment costs and can design your own plans and quotas.

Price tags

Low cost, Self-hosted

Free quota

No unified free quota; depends on the self-hoster's configuration.

Usually you create an API key in the platform console, then replace the SDK's baseURL, model name, and auth details per the docs. Test streaming, function calling, error codes, and rate limits before launch.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AI_GATEWAY_API_KEY,
  baseURL: "https://your-gateway.example.com/v1"
});

const response = await client.chat.completions.create({
  model: "gpt-4.1-mini",
  messages: [{ role: "user", content: "Test one call through an AI gateway." }]
});

• Supported models: OpenAI, Claude, Gemini, DeepSeek, Qwen, Moonshot, Embedding.
• Capabilities: OpenAI-compatible, Streaming, Function calling, Embeddings, Balance query, Log query.
• Documentation completeness: Medium; editorial stability score 3.8 / 5.

• Open-source projects require maintaining security updates yourself; public operation adds compliance, risk-control, and billing work.
• Third-party relay pricing, models, and availability can change, so re-check them periodically.

Is One API compatible with the OpenAI API?

This entry is marked as supporting the OpenAI-compatible format, but the exact base_url, model names, and parameters still follow the official docs.

Is One API ready for production?

Run a small-traffic load test, rate-limit test, and error-code test first, and confirm the billing rules; keep a backup provider for important workloads.