Which models are supported?

A curated set across Anthropic Claude, OpenAI GPT, Google Gemini, Moonshot/Kimi, Zhipu and DeepSeek. We keep the models that earn their place rather than listing every model. The full list lives in the Models catalog.

Is my request data used for training?

No. EzRouter passes requests through to the provider you are routed to and returns the response. We do not retain prompt or completion payloads beyond short-lived debugging logs you control.

What happens if a provider goes down?

The router watches latency, error rate and capacity across every supplier in real time. If one wobbles, the next request silently goes to the next-best provider for that model, with no client change needed.

How do I migrate from OpenAI or OpenRouter?

Swap the base URL in your existing client to the EzRouter endpoint. Request and response shapes match the OpenAI chat-completions schema, so existing SDKs and tooling keep working.

Announcing adaptive model routing

One OpenAI-compatible API for Claude, GPT & Gemini

Q: How do I get an API key?

Sign up and a key is issued in the dashboard immediately. New accounts include $0.10 starter credit, and keys can be scoped or revoked independently.

Q: How is pricing calculated?

Per input and output token, priced below each provider's official API. Our routing layer picks the cheapest stable supplier for every request, and you see the effective rate in your usage logs.

One OpenAI-compatible endpoint for frontier models, dynamic failover, and usage-based pricing. New accounts start with $0.10 API credit.

Get API key Documentation

#	Model	Provider	Price in / out / cache read / write
01	GPT-5.5	OpenAI	In $5 Out $30 Read $0.5 Write $5
02	Claude Opus 4.7	Anthropic	In $5 Out $25 Read $0.5 Write $6.25
03	Kimi K2.6	Moonshot	In $0.95 Out $4 Read $0.16 Write $0.95
04	Claude Sonnet 4.6	Anthropic	In $3 Out $15 Read $0.3 Write $3.75
05	DeepSeek V4 Pro	DeepSeek	In $0.45 Out $0.9 Read $0.0045 Write $0.45
06	GLM-5.1	Z.ai	In $1.4 Out $4.4 Read $0.26 Write $1.4

Illustrative snapshot. Live prices sync from the dashboard; the full catalog lives in the docs.

One gateway for the AI companies your product already uses.

OpenAI

Anthropic

Google

DeepSeek

Moonshot

Qwen

Integrate EzRouter in minutes

Keep your OpenAI-compatible client and move provider selection behind one gateway.

Traffic moves when providers do.

EzRouter continuously compares route health, latency, and price, then sends each request to the best available supplier.

AnthropicUS-east primary

135ms

AnthropicEU-west reserve

175ms

AWS Bedrockus-west-2

215ms

Google Vertexpartner route

255ms

Adaptive provider routing

When a supplier slows down or errors spike, traffic shifts to a healthier route without changing your client code.

Start routing traffic

Test routes in a live Playground

Choose a model, tune generation parameters, inspect the request, and send OpenAI-compatible chat traffic from the dashboard.

User

Compare Claude, GPT, and Gemini for a concise product launch summary.

Assistant · routed via Anthropic

Use one OpenAI-compatible request, keep the prompt stable, and let EzRouter select the healthiest supplier for the selected model route.

1.42s 1,284 tokens $0.0064

Ask a model through EzRouter...

Know the bill before traffic moves.

Model spend is easiest to control when routing, pricing, and logs live in the same system.

Usage preview 50M tokens / month

EzRouter $- you save -

official API $- - more expensive

OpenRouter $- - more expensive

Monthly tokens- Input / output split-

You save $- vs official APIs

Actual charges shown in the dashboard are final. Cache hits can reduce your effective cost substantially.

Start routing

Connect the AI products your team already uses.

EzRouter can connect every platform below through one model gateway, one API key, and one place to see routing, failover, and usage.

Hermes Agent AI agent platform Route memory-based agent workflows through one managed model gateway.

Cherry Studio AI productivity studio Use EzRouter as the API entry for multi-model desktop workflows.

OpenClaw Personal AI assistant Connect assistant tasks to routed model access and shared usage controls.

OpenAI Codex Software engineering agent Support engineering agent calls with centralized model and spend control.

Open WebUI Self-hosted AI platform Configure EzRouter as an OpenAI-compatible endpoint for your workspace.

Cursor AI code editor Bring coding model usage into the same routing and billing layer.

Claude Code Agentic coding system Route Anthropic-compatible coding workflows through EzRouter controls.

GitHub Copilot AI developer tool Connect developer automation workflows to a shared model platform.

Pi Personal AI assistant Support assistant-style experiences with routed provider access.

Build against EzRouter

Use one OpenAI-compatible endpoint for routed model access, Anthropic-compatible agent workflows, usage accounting, and production error handling.

Your first API call Check the docs

Documentation - EzRouter Docs

Documentation

Build against ezrouter

Use one OpenAI-compatible endpoint for routed model access, Anthropic-compatible agent workflows, usage accounting, and production error handling.

Getting started Your first API call API reference Create chat completion Integrations Claude Code

Getting started

Error codes Your first API call Rate limits and capacity Tokens and token usage

Guides

Anthropic API surface Use ezrouter with coding agents JSON output Prompt cache

Everything in your control

Manage model access, API keys, billing, and request logs from one dashboard without touching every provider console.

Usage overview

API keys and models

Request visibility

Status Docs Feedback

Welcome back, user.

This dashboard is scoped to the current site and your own account.

Refresh

Balance $248.72 Wallet balance plus invite credit

Today spend $18.43 Today's consumed quota

Requests 12,984 Total requests recorded

Models 27 Available on this site

Recent activity Latest self logs

2m ago claude-opus-4-7 $0.04

8m ago gpt-5.5 $0.02

21m ago deepseek-v4-pro $0.01

Allowed models Site whitelist after filtering

claude-haiku-4-5 claude-opus-4-7 claude-sonnet-4-6 gpt-5.4 gpt-5.5 kimi-k2.6 deepseek-v4-pro

Before you switch

The questions teams ask before switching.

EzRouter is designed for teams that want model choice without turning provider operations into product work.

How do I get an API key?

Register and create a key in the dashboard. New accounts include $0.10 starter credit, and keys can be scoped or revoked independently.

How is pricing calculated?

Input and output tokens are charged separately. The dashboard shows final usage, effective price, and logs.

What happens if a provider has an incident?

EzRouter tracks route health and moves traffic to a healthy supplier for the same model when a route degrades.

Can I keep my current SDK?

Yes. OpenAI-compatible clients can usually migrate by changing the base URL and API key.

Is request data used for training?

No. Requests pass through to the selected provider. Prompt and completion payloads are not retained beyond logs you control.

Need a human?

Email [email protected] and we will reply within one business day.