All ModelschatKimi K3

Kimi K3

by MoonshotPremium

Try on Kunya
chat

Kimi K3

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

Model ID:kimi-k3

API Documentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true
}
cURL example
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}'

Notes

  • 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.

Pricing

Input$3.9 per 1M tokens
Output$19.5 per 1M tokens
Context Window1049K

Capabilities

Streaming Yes
Vision Yes
Reasoning Yes
Tool Use Yes
ProviderMoonshot
Try on Kunya

Similar Models

Kimi K2.7 Code

Moonshot

Coding-focused MoE model for long-horizon programming, agentic task decomposition, and multimodal reasoning

API Documentation

Qwen 3.5 Plus

Qwen

Legacy — superseded by Qwen 3.7 Plus (routes to qwen/qwen3.7-plus).

API Documentation

GPT-5.6 Sol

OpenAI

Frontier GPT-5.6 model for complex professional work, coding, and agentic tasks

API Documentation

Grok 4.5

xAI

Frontier Grok for coding, agentic tasks, and knowledge work — tool calling, web/X search, code execution

API Documentation