Wszystkie modelechatQwen 3.8 Flash

Qwen 3.8 Flash

od QwenSzybki

Wypróbuj na Kunya
Q
chat

Qwen 3.8 Flash

Next-gen multimodal reasoning MoE — coding, agentic workflows, visual and long-video analysis, document and codebase understanding, 1M context

ID modelu:qwen3.8-flash

Dokumentacja API

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Treść żądania
{
  "model": "qwen3.8-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true
}
Przykład cURL
curl -X POST https://kunya.ai/api/v1/chat/completions \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"qwen3.8-flash","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true}'

Uwagi

  • •OpenAI-compatible endpoint — works with any Kunya API key.
  • •Set `"stream": true` for server-sent events.
  • •Supports vision: pass image URLs in message content as `{ "type": "image_url", "image_url": { "url": "..." } }`.
  • •Supports tool calling via the `tools` parameter.

Ceny

Wejście$0.208 za 1M tokenów
Wyjście$0.611 za 1M tokenów
Okno kontekstu1000K

Kunya benchmark

Updated 2026-10-06 · #14 performance · #6 value

Performance
95.1
Value (KVI)
115.0
Literary writing
97.0
Cost
$0.97/1k tasks
Full benchmark report →

Możliwości

Streaming Tak
Wizja Tak
Rozumowanie Tak
Narzędzia Tak
DostawcaQwen
Wypróbuj na Kunya

Podobne modele

MiMo v2.6 Flash

Xiaomi

309B MoE open foundation model — 1M context, native multimodal, strong coding and agentic workflows at low cost

Dokumentacja API

Qwen 3.7 Flash

Qwen

Fast vision-language reasoning model — multimodal agents, visual coding, search, and computer interaction with 1M context. Web search via Kunya tools + smart-search fallback when native tool calls stall.

Dokumentacja API

Gemini 3.5 Flash-Lite

Google

Fastest 3.5-class model — high-throughput chat, tools, and vision at lower cost than full Flash

Dokumentacja API

Gemini 3.8 Live Extended Thinking

Google

High-reasoning Live API model for complex multi-step voice interactions with background tool use

Dokumentacja API