Enterprise AI API Gateway

One Key. Every Leading
AI Model.

OpenAI-compatible. Claude and GPT, unified behind a single gateway. Reliable routing, transparent billing, production-ready from day one.

Technology shouldn't stand above people — it should serve them.

Connected Models
Claude Opus 4.8 Claude Opus 4.7 Claude Opus 4.6 Claude Sonnet 4.5 Claude Haiku 4.5 GPT-5.5 GPT-5.6 Sol GPT-5.6 Terra Claude Opus 4.8 Claude Opus 4.7 Claude Opus 4.6 Claude Sonnet 4.5 Claude Haiku 4.5 GPT-5.5 GPT-5.6 Sol GPT-5.6 Terra

Why Ainzy

Built for reliability and cost efficiency, so you can focus on your product

Smart Multi-Channel Routing

Real-time health checks across every upstream provider. Failing channels are isolated automatically — your traffic never notices.

Transparent, Usage-Based Billing

Live usage and billing in your dashboard. No minimums, no hidden fees — every token accounted for.

OpenAI-Compatible Protocol

Swap the base URL and key — your existing SDKs and frameworks keep working, zero code changes required.

30+
Model Providers
99.9%
Uptime
<200ms
Routing Latency
24/7
Monitoring

Frequently Asked Questions

Models, pricing, billing, and how to get connected

How do I get started?

Create an account and confirm the code we email you, generate an API key in the console, then point your base URL at https://ainzy.net/v1. If your code already talks to OpenAI, changing the base URL and the key is the whole migration.

Which models are available?

On the Default group: Claude Opus 4.6, 4.7 and 4.8, Claude Sonnet 4.5 and Claude Haiku 4.5. On Plus and Pro: GPT-5.5, GPT-5.6 Sol and GPT-5.6 Terra. The model page also lists entries that are still being wired up, so if you want to build against something outside this list, ask us first and we will confirm it is live.

Which API formats do you speak?

Three, on the same key and the same host: OpenAI /v1/chat/completions, OpenAI /v1/responses, and Anthropic /v1/messages. Streaming works on all three. Whichever SDK you already use, there is a good chance it works untouched.

Can I use it with Claude Code or Codex?

Yes. Point them at the Ainzy gateway and they work as-is. The easiest route is CC Switch, a free desktop tool that stores the settings for you and lets you switch providers from the tray — our setup guide walks through both Codex and Claude Code.

What do Default, Plus and Pro mean?

They are the groups a key can belong to, and the group decides both which models the key can reach and what you pay. Default covers the Claude models at official pricing. Plus and Pro cover GPT and Codex at 10% and 20% of list price respectively. Pick the group when you create the key; one account can hold keys in several groups.

How does billing work?

Per token, on actual usage, multiplied by your group’s rate — no subscription and no monthly minimum. Every request lands in the console log with its token counts and cost, so the bill is auditable line by line. Requests that fail upstream are not billed.

How do I add credit?

There is no self-serve checkout on this site yet, so credit is added manually — email us and we will set it up. New accounts start at a zero balance, so registering on its own does not grant any usage; get in touch if you want to evaluate the service first.

How is reliability guaranteed?

Redundant upstream providers with continuous health monitoring. Failing channels are isolated and routed around automatically, and failed requests are never billed to you.

Something is wrong — how do I reach you?

Start with the console log: it records the exact upstream error and the request ID for every call, which usually answers the question on its own. If it does not, email us with that request ID and we can trace the request end to end.

Migrate & Get Rewarded

Multi-provider failover, transparent billing, 24/7 uptime — this is our first product, and we're serious about teams making the switch. Two grants, ready for you.

Enterprise

Enterprise Migration Grant

Up to
100M tokens

For teams and production workloads. Show us your in-progress project or usage history on another platform — dedicated onboarding, approved on the spot.

Developer

Developer Support Grant

Up to
30M tokens

For independent developers and early-stage projects. Show us your project or usage history elsewhere — qualifying requests are approved as a grant.

Start a conversation

Partnerships, migration grants, or technical support — reach us directly and we'll get you set up.

Start building today

Set up in minutes — one key, every leading model

Get API Key →