Wszystkie modelechatKimi K3

Kimi K3

od MoonshotPremium

Wypróbuj na Kunya
chat

Kimi K3

2.8T MoE flagship for complex coding, knowledge work, and long-horizon agentic workflows with 1M context and native vision

ID modelu:kimi-k3

Dokumentacja API

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Treść żądania
{
  "model": "kimi-k3",
  "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":"kimi-k3","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$3.9 za 1M tokenów
Wyjście$19.5 za 1M tokenów
Okno kontekstu1049K

Kunya benchmark

Updated 2026-10-06 · #8 performance · #20 value

Performance
95.9
Value (KVI)
60.9
Literary writing
81.3
SWE Verified
93.4%
Cost
$18.47/1k tasks
Full benchmark report →

Możliwości

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

Podobne modele

Qwen 3.7 Plus

Qwen

Cost-effective Qwen3.7 VL model — 1M context, vision + tools + agent workflows, GUI and mobile navigation

Dokumentacja API

MiMo v2.6 Pro UltraSpeed

Xiaomi

Same 1T MiMo v2.6 Pro checkpoint with ~10× output speed — 1M context multimodal agentic workflows

Dokumentacja API

GPT-6 Astra

OpenAI

OpenAI flagship for complex reasoning, coding, computer use, and agentic work

Dokumentacja API

MiniMax M3

MiniMax

M-series flagship — 1M context, agentic coding, tool use, vision + video input, interleaved thinking

Dokumentacja API