AI Rate Card

qwen3-next-80b-think · poe
давно не подтверждено

Try https://poe.com/Qwen3.8-Flash for the first-party Qwen bot. Qwen3-Next uses a highly sparse MoE design: 80B total parameters, but only ~3B activated per inference step. Experiments show that, with global load balancing, increasing total expert parameters while keeping activated experts fixed steadily reduces training loss.Compared to Qwen3’s MoE (128 total experts, 8 routed), Qwen3-Next expands to 512 total experts, combining 10 routed experts + 1 shared expert — maximizing resource usage without hurting performance. The Qwen3-Next-80B-A3B-Thinking excels at complex reasoning tasks — outperforming higher-cost models like Qwen3-30B-A3B-Thinking-2507 and Qwen3-32B-Thinking, outpeforming the closed-source Gemini-2.5-Flash-Thinking on multiple benchmarks, and approaching the performance of our top-tier model Qwen3-235B-A22B-Thinking-2507. File Support: Text, Markdown and PDF files Context window: 131k tokens

Базовая модельВсе модели этой базовойВсе модели провайдерак провайдеру

Читайте также: Цены на API Qwen: Qwen3.8 Max, Plus, Flash, 27B и открытые модели у всех провайдеров

Все модели Qwen у всех провайдеров

Вход, $/1M $0.15

Выход, $/1M $1.52

Контекст —

Принимает текст

Последняя проверка 04.11.2026 12:26:37 UTC

Источник страница провайдера

Уведомления о ценах

Войдите, чтобы следить за ценой

API

API, совместимый с OpenAI: подходят официальные SDK OpenAI с этим адресом. YOUR_API_KEY замените на свой ключ от провайдера.

Адрес API
https://api.poe.com/v1
Эндпоинт
https://api.poe.com/v1/chat/completions
Модель (id в API)
qwen3-next-80b-think
curl
curl https://api.poe.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3-next-80b-think", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 256}'
Python
import requests

r = requests.post(
    "https://api.poe.com/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "model": "qwen3-next-80b-think",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ],
      "max_tokens": 256
    },
)
print(r.json())
JavaScript
const r = await fetch("https://api.poe.com/v1/chat/completions", {
  method: "POST",
  headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
  body: JSON.stringify({
    "model": "qwen3-next-80b-think",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "max_tokens": 256
  }),
});
console.log(await r.json());
Запрос (JSON)
{
  "model": "qwen3-next-80b-think",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}
Ответ (JSON)
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "qwen3-next-80b-think",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Адрес взят из списка моделей провайдера - сверьте с его документацией.

Документация API провайдера

Source: AI Rate Card, https://airatecard.com/ru/c/offer%3Apoe%7Cqwen3-next-80b-think, prices checked 2026-11-04; seller's page: https://poe.com/qwen3-next-80b-think

Технические данные

ID: offer:poe|qwen3-next-80b-think