ARK Cloud · Sovereign inference

Welcome back, Andreas.

Your workspace is ready. Track usage, run a quick test, and ship against the OpenAI v1-compatible API — zero retention, EU-hosted by default.

Add credits Read the docs →
Credit balance

Usage & credits

49,545,299Credits
↑ 4.2% week over week · ≈ 18 days of runway at current pace
Active balance
2.4M 1.8M 1.2M 0.6M Apr 12 Apr 13 Apr 14 Apr 15 Apr 16 Apr 17 Today
Requests (7d) 12,384
Credits burned 1.87M
Avg latency 312 ms
Error rate 0.04%
Authentication

Your API key

Live
sk-ark-•••••••••••••••••••••••••••••896d 
# cURL — POST /v1/chat/completions
curl https://api.ark-labs.cloud/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "ark-mistral-large",
    "messages": [{"role":"user","content":"Hello, ARK."}],
    "temperature": 0.7
  }'

Use this key to authenticate requests to the ARK Labs API. Keep it secret and secure. Leaked keys can be rotated instantly.

Playground

Test a model without leaving the dashboard

Region: EU-Central
Prompt /v1/chat/completions
Press ⌘ + Enter to run
Response Streaming · 312 tok/s
EU AI Act in three bullets:
  1. Risk-tiered framework: unacceptable, high, limited, minimal. High-risk AI must meet conformity, documentation, and human-oversight requirements.
  2. Transparency duties for general-purpose and generative models, including technical documentation, copyright disclosure, and synthetic-content labelling.
  3. Phased enforcement 2025–2027, with fines up to €35M or 7% of global turnover for prohibited-use violations.
284 tokens in 412 tokens out 1.34 s latency cost ≈ 0.012€
Request log

Recent activity

Last 20 requests
Endpoint Model Tokens Latency Status Time
POST /v1/chat/completions ark-mistral-largeMistral AI · 123B 696 1.34 s 200 OK just now
POST /v1/embeddings ark-bge-m3BAAI · embedding 4,120 220 ms 200 OK 2 min ago
POST /v1/chat/completions ark-llama-3.1-70bMeta · 70B 1,284 2.08 s 200 OK 7 min ago
POST /v1/chat/completions ark-qwen-2.5-72bAlibaba · 72B 312 890 ms 429 Throttled 12 min ago
POST /v1/chat/completions ark-deepseek-v3DeepSeek · 671B MoE 2,058 3.17 s 200 OK 28 min ago
POST /v1/chat/completions ark-mistral-largeMistral AI · 123B 844 1.52 s 200 OK 41 min ago

Need help getting started?

Clear guides, working examples, and SDK snippets — from first call to production config, everything you need to make the most of your credits and API.

Quickstart View documentation →