Volver a modelos
Thinking Machines Lab
Inkling Small
MoEotherPublicado el 31 jul 2026
An open-weight multimodal mixture-of-experts model from Thinking Machines Lab with 12B active parameters out of 276B total, positioned as the smaller, more efficient member of the Inkling family. Accepts text, image, and audio input with reasoning, tool use, and a 524K-token context window.
ChatCompletar textoLlamada a funcionesVisiónAudioGeneración de códigoRazonamientotext · image · audio · code
Proveedores (1)
Ordenados por coste total (entrada y salida por 1 millón de tokens). Selecciona una fila para ver los detalles del proveedor.
| Proveedor | Precio (por 1 M) | Límites | Regiones | Estado | Latencia |
|---|---|---|---|---|---|
 | Entrada: $0.45Salida: $1.20 | 60 RPM / 200K TPM | us-east-1 | Operativo | 0ms |
Inicio rápido
Usa este modelo mediante OpenRouter con un SDK compatible con OpenAI.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const response = await client.chat.completions.create({
model: "thinkingmachines/inkling-small",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);API de OpenRouter · SDK compatible con OpenAI