Built for OpenClacky

Top-Tier Model Access, Optimized for Your Workflow

Deeply optimized for flagship reasoning models and turbo high-speed models. Stable routing, smart caching, zero markup.

Pay-as-you-go · No subscription · Auto top-up supported

Why OpenClacky AI Keys

One Key, every top-tier model

Claude, Gemini, DeepSeek — all in one place. Best reasoning × best value × best vision, without juggling multiple accounts, keys, and bills.

One Key, every model

Unified access to all major models — Claude, Gemini, DeepSeek. Switch by alias, top up once, use everywhere.

Reasoning + value + vision, all-in-one

Claude leads deep reasoning, DeepSeek V4 nails cost-efficiency, Gemini brings native multimodal and image generation.

Stable, low latency, official pricing

Globally reachable proxy at official rates (only 5% service fee). Near-100% cache hit cuts long-conversation cost by ~50%.

Three flagship lineups in one place

Flagship reasoning

Claude Series

Anthropic's flagship — top-tier reasoning and code generation. Native prompt caching: cache hits cost just 10% of input price.

Opus 4.8 / 4.7 · Sonnet 4.6 / 4.5 · Haiku 4.5
Multimodal & image

Google Gemini Series

1M-token long context, natively multimodal. Three new models — 20% off — including Nano Banana 2 fast image gen and Pro Image.

Gemini 3.1 Pro · 3.5 Flash · 3 Pro / 3.1 Flash Image
Cost-efficient

DeepSeek Series

V4-Pro permanently 75% off. Combined with 99% cache hit rate, total cost on long conversations drops another 50%.

DeepSeek V4 Pro · V4 Flash
Permanent price cut

DeepSeek V4-Pro is now 75% cheaper — forever

AI Keys automatically apply the new price. No action needed.

With 99% cache hit rate, costs drop another 50%.

Input / 1M tokens
$1.74
$0.435
Output / 1M tokens
$3.48
$0.87
Cache hit / 1M tokens
$0.0145
$0.003625
Create AI Key →
New · 20% off, limited time

Three new Google Gemini models are live

1M long context + native image generation. The whole Vertex Gemini lineup is 20% off, applied automatically at billing.

Promo per-image cost: Flash Image ≈ $0.064, Pro Image ≈ $0.128.

or-gemini-3-5-flash
Cost-effective general text
or-gemini-3-pro-image
High-quality image generation
or-gemini-3-1-flash-image
Nano Banana 2 — fast image gen
View models →

Why Not Just Use Your Own API Key?

Unreliable Connectivity

Direct API connections often suffer high latency, timeouts, and rate limits that break your agent mid-task.

Unpredictable Billing

Token-based pricing from multiple providers is hard to track. Unexpected bills kill momentum.

Compatibility Risk

Different providers use varying API standards, which can cause compatibility issues when switching or mixing them — quietly breaking your Agent's reliability.

How It Works

1

Top Up Your Balance

Add $20 to start. Pay-as-you-go, no subscription.

2

Generate an AI Key

One key for all models. Paste it directly into OpenClacky settings.

3

Use the Best Models

Enjoy optimized, cached access to top models with transparent per-request pricing.

Why AI Keys?

Stable, Optimized Routing

Direct connections to top-tier cloud infrastructure, tuned specifically for OpenClacky workloads. No middleman hops, no fragile tunnels. Sub-second response times instead of minute-long waits.

Response latency
Minutes
Sub-second

Zero Markup

You pay exactly what the model providers charge. No reseller margin. No hidden fees. Just 5% for payment processing. No monthly subscription.

Our markup
0%

Industry-Leading Cache Hit Rate

While OpenRouter achieves ~90% cache hit rates, AI Keys reaches 99%. Every cache hit saves 90% of the token cost. The result: up to 50% lower overall spend without changing a single line of your workflow.

Cache hit rate
OpenRouter 90%
AI Keys 99%
Cost reduction
50%↓

Frequently Asked Questions

What is AI Keys?
AI Keys is a managed model access service built for OpenClacky. One key gives you access to Claude (Opus 4.8/4.7, Sonnet 4.6/4.5, Haiku 4.5), Google Gemini (3.1 Pro / 3.5 Flash / 3 Pro Image / 3.1 Flash Image) and DeepSeek (V4-Pro / V4-Flash) — with stable routing and smart caching.
How is it different from buying API keys directly?
Direct API keys require separate accounts, different configurations, and individual billing for each provider. AI Keys gives you one unified key, one balance, and one pricing table.
Which models are supported and how do I switch?
Currently Claude, Gemini, and DeepSeek series — full list and pricing at /docs/ai-key-models. Inside OpenClacky just switch by model alias; no need to reconfigure your key.
What is the Gemini 20%-off promotion?
To celebrate the launch of gemini-3.5-flash, gemini-3-pro-image, and gemini-3-1-flash-image, every Vertex Gemini model is now 20% off (final price including the 5% service fee, then ×0.8). No setup required — just call the model. We'll announce the end of the promotion in advance.
What is cache hit rate? How does it cut cost by another 50%?
Claude and DeepSeek support prompt caching: identical prefixes are billed at as low as 10% of normal input rates on hit. In agent workflows with repeated system prompts the hit rate can reach 99%, cutting overall input cost by ~50%.
What does it cost?
You pay the official model rates with no markup. We add 5% to cover payment processing. Some models also have limited-time promotions (e.g. all Vertex Gemini models are 20% off right now), and with near-100% cache hits the total cost of long conversations drops another ~50%. No monthly fee, no hidden charges.
Is my data safe?
Requests are forwarded to providers with no data retention on our side. We do not use your data for training.
Can I set a spending limit?
Yes. You can configure a monthly spending cap from your Creator Hub at any time.

Ready to Start?

Top up $20 and get your AI Key in under a minute.

Top Up Now →

Already have an account? Sign in