Portkey AI Gateway gateway details

An enterprise-oriented AI Gateway focused on a unified interface, routing, fallback, observability, and logging; ideal for teams needing to govern multi-model calls.

Best for: For enterprise dev teams needing multi-provider governance, auditing, fallback, and cost attribution.

Current status

Reachable

Latency reference

860 ms

/models check

Provider routing

Last verified

2026-07-01

Status notes

Leans toward enterprise governance, logging, and routing; good for managing multiple providers.

Pricing mode

Mainly SaaS plans and enterprise billing; model cost usually comes from the underlying providers you connect.

Price tags

High stability, Plan-based

Free quota

Refer to the official plans page.

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, Embedding.
• Capabilities: OpenAI-compatible, Streaming, Function calling, Embeddings, Log query.
• Documentation completeness: High; editorial stability score 4.4 / 5.

• Not a plain low-cost relay; understand the relationship between gateway fees and underlying model fees.
• Third-party relay pricing, models, and availability can change, so re-check them periodically.

Is Portkey AI Gateway 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 Portkey AI Gateway 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.