Kimi K3 (Moonshot)SOTA Frontier
Provider: Moonshot AI · License: custom
Moonshot AI flagship 2.8T MoE architecture featuring Kimi Delta Attention (KDA) with 1,000,000 token context window for full-repository analysis.
#1m-context#long-horizon#codebases#frontier
Architecture & Execution Specs
Parameter Scale2.8T MoE
Context Horizon1.0M tokens
Attention MechanismKimi Delta Attention (KDA)
Serving RuntimevLLM / SGLang (Continuous Batching)
Precision StandardFP8 / BF16 Native
Inference Pricing & Economics
Input Cost / 1M Tokens$3.75/M
Output Cost / 1M Tokens$18.75/M
Effective Operational Markup+20% over bare compute
Self-Hosting Break-Even~80M monthly tokens
SLA Availability99.9% Enterprise Tier
cURL API Integration
curl https://osi.arcanetechnologies.org/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer osi_live_YOUR_KEY" \
-d '{
"model": "kimi-k3",
"messages": [
{ "role": "system", "content": "You are a senior algorithmic systems engineer." },
{ "role": "user", "content": "Analyze the time complexity of distributed sparse all-to-all communications." }
],
"temperature": 0.6
}'