Qwen Turbo Latest (thinking) API

Qwen Turbo Latest (thinking) es un modelo de razonamiento de Alibaba Qwen. Ofrece razonamiento paso a paso. Disponible a través de la API unificada de MeshTok.

RazonamientoRápido

Precios (oficial, por 1M tokens)

Entrada

$0.50/M

Salida

$1.50/M

Especificaciones

Ventana de contexto128K tokens Modalidades de entradaTexto StreamingSí APICompatible OpenAI

Cómo usar Qwen Turbo Latest (thinking)

Reemplazo directo de OpenAI. Cambia solo base_url y modelo.

# Python - pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://meshtok.com/v1",
    api_key="sk-your-MeshTok-key",
)

resp = client.chat.completions.create(
    model="ali/qwen-turbo-latest:thinking",
    messages=[{"role":"user","content":"Hello!"}],
)
print(resp.choices[0].message.content)

# cURL
curl https://meshtok.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-MeshTok-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"ali/qwen-turbo-latest:thinking","messages":[{"role":"user","content":"Hello!"}]}'