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.
moonshotai/kimi-k3
- Contexto
- 1M tokens
- Máx. completion
- —
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-07-16
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
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"}]
}'Consigue tu API keyPreguntas frecuentes
- ¿Qué es 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 corre en el API de Geek Hub (compatible con OpenAI). Id: moonshotai/kimi-k3.
- ¿Kimi K3 es gratis?
- No. El input cuesta $3.2702 / 1M tokens y el output $16.3509 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Kimi K3?
- Kimi K3 tiene una ventana de 1M tokens.
- ¿Kimi K3 soporta tool calling y structured outputs?
- Kimi K3 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Kimi K3?
- Kimi K3 se lanzó el 16 de julio de 2026.
Más modelos de Moonshot
Kimi K2 0711Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. I
Kimi K2 0905Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trilli
Kimi K2 ThinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-
Kimi K2.5Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued p
Kimi K2.6Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end
Kimi K2.7 CodeMoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native m