New API gateway details

An open-source multi-channel gateway evolved from the One API ecosystem, with more model channels, billing features, and operational config; ideal for webmasters or teams self-hosting a unified API entry point.

Best for: For teams or webmasters needing self-hosted multi-model relay, quota management, and channel distribution.

Current status

Test yourself

Latency reference

Depends on your deployment

/models check

See the platform docs

Last verified

Not verified yet

Status notes

Test plain responses, streaming, error codes, and rate limits yourself before launch.

Pricing mode

Open-source and self-hosted; cost depends on servers, upstream model channels, and your own billing strategy.

Price tags

Low cost, Self-hosted

Free quota

No unified free quota; configured by the self-hoster.

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, Midjourney, TTS.
• Capabilities: OpenAI-compatible, Streaming, Image generation, Balance query, Log query.
• Documentation completeness: Medium; editorial stability score 3.8 / 5.

• Public operation means owning key security, channel compliance, billing risk-control, and user-data protection.
• Third-party relay pricing, models, and availability can change, so re-check them periodically.

Is New 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 New 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.