One-click access
Get one API key and call every connected AI model without applying for each provider separately.
Multi-model compatible, enterprise-ready
Every model.
One key. Flat rate.
flatkey.ai unifies model access, routing, billing, usage analytics, and operational controls for teams shipping AI products.
At least 40% cheaper than official
Route Codex and Claude Code usage through Flatkey, keep the workflow, cut metered spend.
Take over existing coding-agent traffic now
One installer configures Codex CLI or Claude Code to use router.flatkey.ai in about 30 seconds.
Works with your current tools
Supports one-click configuration and perfectly adapts to NewAPI multi-protocol configuration.
Cherry Studio
CC Switch
More Apps
200 ok
POST
https://console.flatkey.ai/v1/chat/completionsRequest
curl -X POST "https://console.flatkey.ai/v1/chat/completions" \
-H "Authorization: Bearer sk-fk-••••" \
-H "Content-Type: application/json" \
-d '{
"model": "your-model",
"messages": [
{ "role": "user", "content": "..." }
]
}'
Response
{
"choices": [{ "message": { "content": "Chat request routed." } }],
"usage": { "total_tokens": 27 }
}
142ms27tokensCost$0.00081
stream · sseAt least 40% cheaper than official
Quick install
One command sets up the local agent, asks which tool to take over, and points usage to Flatkey.
macOS one-liner
curl -fsSL https://flatkey.ai/install.sh | bash
Flatkey one-line install commands
macOS: curl -fsSL https://flatkey.ai/install.sh | bash
Linux: curl -fsSL https://flatkey.ai/install.sh | bash
Windows: iwr https://flatkey.ai/install.ps1 -UseBasicParsing | iex
200+models behind one key
1OpenAI-compatible base URL
24/7usage and billing visibility
1dashboard for keys and routing
Why flatkey
One place for access,
pricing, and control
Stable and reliable
Intelligently route multiple upstream accounts with automatic switching and load balancing to avoid frequent errors.
Pay as you go
Bill by actual usage, set quota limits, and keep team consumption clear at a glance.
Recommended AI models
Curated top models selected by the flatkey community
GPT Image 2
$4 / 1M
text-to-text
Seedance 2.0
$0.063 / sec
text-to-text
Claude Opus 4.7
$4 / 1M
text-to-text
Claude Sonnet 4.6
$2.4 / 1M
text-to-text
AIDeepSeek V4 Pro
AIMiniMax-M2.7
AIGPT-5.4 nano
AIGPT-5.4 mini
AIGPT-5.4 pro
AIDeepSeek V4 Pro
AIMiniMax-M2.7
AIGPT-5.4 nano
AIGPT-5.4 mini
AIGPT-5.4 pro
About flatkey.ai
A unified API layer for modern AI products
flatkey.ai provides hosted software and prepaid account balance for metered AI API usage. Usage charges are calculated from model input, output, and cache-hit prices multiplied by token usage.
What flatkey.ai is
flatkey.ai is a unified AI API gateway that lets teams call supported AI models through one API key, one base URL, and one dashboard.
Problem it solves
It reduces separate provider accounts, scattered API keys, inconsistent routing, and fragmented usage tracking for teams building AI features.
Who uses it
flatkey.ai is built for developers, AI product teams, automation builders, and operations teams that need predictable access to multiple models.
Product focus
Built for teams shipping AI features
flatkey keeps model access, routing, billing, and usage policy in one place so teams can move faster without extra provider management.
AI product teams
Add model access to your product without managing separate provider accounts, keys, and SDK changes.
Operations and finance
Keep token spend, recharge records, and team usage visible in one dashboard.
Automation builders
Route high-volume workflows to suitable models while keeping failures and cost easier to review.
Model evaluation and iteration
Compare providers, switch models, and keep existing OpenAI-compatible clients pointed at the same base URL.
How it fits together
From homepage to production calls
1
Get one key
Create a flatkey account, open the dashboard, and generate an API key for your app.
2
Change the base URL
Point your OpenAI-compatible client to https://console.flatkey.ai/v1 and keep your existing SDK.
3
Monitor and optimize
Review usage, cost, routing, and errors from the same product dashboard.
Ready to replace
model chaos with one key?
Start from the flatkey homepage, manage your product dashboard, and keep console.flatkey.ai as the stable API endpoint.