by QwenPremium
Qwen4 Max
Qwen4 flagship — pay-as-you-go via OpenRouter (Alibaba Cloud Int.); multimodal reasoning, tools, 1M context; cheaper than Token Plan direct preview
qwen4-maxGenerate chat completions with this model.
/api/v1/chat/completionsGET /api/v1/models?type=chat{
"model": "qwen4-max",
"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":"qwen4-max","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"max_tokens":4096}'Sakana
Japanese-specialized reasoning model based on Kimi K2.6 — instruction following, business writing, math, coding, research, and agent workflows. Built-in web search and code execution (billed separately by provider). Sakana may use inputs for training by default (opt-out in Sakana Console).
API DocumentationXiaomi
Native omnimodal model — Pro-level agentic performance at half the cost, with image & video understanding and 1M context
API DocumentationAnthropic
Previous Fable — demanding reasoning, complex agentic coding, and long-horizon work with 1M context
API DocumentationAnthropic
Hybrid reasoning model with 1M context, top-tier coding and agentic performance
API Documentation