Kimi K3

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.

ChatMoonshot1M tokens$3.2702 / $16.3509 · 1M

moonshotai/kimi-k3

Context
1M tokens
Completion cap
—
Tools
Yes
JSON
Yes
Released
2026-07-16

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k3",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Kimi K3?
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency. Kimi K3 runs on the Geek Hub API (OpenAI-compatible). Model id: moonshotai/kimi-k3.
Is Kimi K3 free?
No. Input is $3.2702 per 1M tokens and output is $16.3509 per 1M tokens on Geek Hub (markup included).
What is the context length of Kimi K3?
Kimi K3 has a 1M tokens context window.
Does Kimi K3 support tool calling and structured outputs?
Kimi K3 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Kimi K3 released?
Kimi K3 was released on 2026-07-16.

More models from Moonshot