302.AI gateway details

A tool and API aggregation platform covering text, image, video, and audio AI capabilities; ideal for individuals and small teams wanting one-stop access to many models.

Best for: For users who want to quickly try many kinds of AI tools without signing up for multiple overseas services.

Current status

Test yourself

Latency reference

620 ms

/models check

See the console

Last verified

2026-07-01

Status notes

Broad coverage, but pricing and model availability change quickly — test with a small balance.

Pricing mode

Billed per tool or model usage; the site lists separate prices per model.

Price tags

Standard price, Signup credit, Pay-as-you-go

Free quota

The site claims a free quota; actual amount depends on your account after signup.

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: "see the platform docs"
});

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, Grok, Qwen, Moonshot, Doubao and more.
• Capabilities: OpenAI-compatible, Streaming, Image generation, Speech-to-text, TTS, Embeddings, Balance query.
• Documentation completeness: Medium; editorial stability score 4.0 / 5.

• Model prices, available models, and API compatibility change fast; test with small amounts before launch.
• Third-party relay pricing, models, and availability can change, so re-check them periodically.

Is 302.AI 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 302.AI 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.