av MoonshotPremium
Kimi K3
2.8T MoE flagship for complex coding, knowledge work, and long-horizon agentic workflows with 1M context and native vision
kimi-k3Generate chat completions with this model.
/api/v1/chat/completionsGET /api/v1/models?type=chat{
"model": "kimi-k3",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": false,
"thinking": true
}curl -X POST https://kunya.ai/api/v1/chat/completions \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"kimi-k3","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true}'Updated 2026-10-06 · #8 performance · #20 value
Moonshot
Coding-focused MoE model for long-horizon programming, agentic task decomposition, and multimodal reasoning
API-dokumentationMoonshot
State-of-the-art visual coding and agentic tool-calling with multimodal reasoning
API-dokumentationAnthropic
Hybrid reasoning model with 1M context, top-tier coding and agentic performance
API-dokumentationAnthropic
Previous Sonnet — prefer Claude Sonnet 5.5 for speed and cost per task
API-dokumentation