Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

Speech-to-textThinkingmachines1M tokens$1.0356 / min

thinkingmachines/inkling

Contexto
1M tokens
Máx. completion
262,144
Tools
Sí
JSON
Sí
Lanzamiento
2026-07-17

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": "thinkingmachines/inkling",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es Inkling?
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text. Inkling corre en el API de Geek Hub (compatible con OpenAI). Id: thinkingmachines/inkling.
¿Inkling es gratis?
No. $1.0356 por minuto en Geek Hub.
¿Cuál es el contexto de Inkling?
Inkling tiene una ventana de 1M tokens. Soporta hasta 262,144 tokens de completion.
¿Cuándo se lanzó Inkling?
Inkling se lanzó el 17 de julio de 2026.

Más modelos de Thinkingmachines