Skip to main content
Flatkey is an AI API gateway that gives you a single OpenAI-compatible endpoint for 300+ official models from OpenAI, Anthropic, Google, DeepSeek, Qwen, GLM, and more, plus access to 1000+ tools. Change your base_url to https://router.flatkey.ai/v1, keep your existing code, and start saving immediately — models are priced at up to 50% off official list.

Quickstart

Make your first API call in under 5 minutes

API Reference

Full endpoint reference with request and response examples

Model Directory

Browse all 300+ models, providers, and live pricing

Pricing & Credits

Understand subscription plans, usage billing, and account credits

How Flatkey works

1

Create your account

Sign up at console.flatkey.ai and choose the subscription plan that fits your usage.
2

Generate an API key

Open the Keys section in the dashboard and create a new API key. Keep it secret — treat it like a password.
3

Point your client to Flatkey

Set base_url to https://router.flatkey.ai/v1 in your OpenAI-compatible SDK. No other code changes required.
4

Monitor usage and costs

Track every request, token count, and dollar spent in the Usage dashboard. Set quotas to cap spend.

Why teams use Flatkey

One key, every model

Access GPT, Claude, Gemini, DeepSeek, Qwen, GLM, and more with a single API key and base URL.

Up to 50% savings

Models are priced at up to 50% off the official list price.

99.9% success rate

Automatic failover across upstream providers. Live health dashboards for every model.

Zero data retention

No storage of prompts or completions. GDPR compliant, SOC 2 and ISO 27001 aligned.

Drop-in replacement

OpenAI-compatible API. Change one line of code — no SDK rewrites, no migration overhead.

Subscription billing

Choose a plan that fits your workload and monitor usage in real time.

Explore the docs

Authentication

Learn how to create and use your Flatkey API key

OpenAI SDK Guide

Use Flatkey with the official OpenAI Python or Node.js SDK

Anthropic SDK Guide

Route Claude requests through Flatkey with the Anthropic SDK

Model Health

View real-time success rates and latency for every model