av OpenAISnabb
GPT-5.6 Luna
Cost-efficient GPT-5.6 model for high-volume workloads and subagent loops
gpt-5.6-lunaGenerate chat completions with this model.
/api/v1/chat/completionsGET /api/v1/models?type=chat{
"model": "gpt-5.6-luna",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": false,
"thinking": true,
"max_tokens": 4096
}curl -X POST https://kunya.ai/api/v1/chat/completions \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"gpt-5.6-luna","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"max_tokens":4096}'OpenAI
Fast, cost-efficient GPT-6 model for chat, classification, high-volume agents, and subagent loops
API-dokumentationKunya
Admin-only fast stack — Gemini 3.8 Flash execution + GLM 5.3 Flash budget tiers. Maximum speed/cost ratio.
API-dokumentationStepFun
196B MoE multimodal model — native image & video understanding, selectable reasoning depth
API-dokumentationMost intelligent Flash model — long-horizon software engineering, autonomous agents, and enterprise workflows at Flash speed (intro pricing through Dec 2026)
API-dokumentation