Qwen3.6-Flash-2026-04-16 API
ID модели в запросах:global-3/qwen3.6-flash-2026-04-16
Qwen3.6-Flash-2026-04-16 от Qwen через один OpenAI-совместимый API Nodul Router: ключ с лимитами, журнал запросов, оплата в рублях.
- Контекст
- 1 000 000
- Макс. ответ
- 65 536
- Выпущена
- 17.04.2026
Цены за 1 млн токенов, ₽Цены за 1 млн токенов, PnP
| Регион | Попробовать | Вход | Выход | Чтение кэша | ID модели в запросах |
|---|---|---|---|---|---|
| Глобальный · global-3 | Попробовать | 25,00 ₽0,25 PnP | 150 ₽1,50 PnP | — | global-3/qwen3.6-flash-2026-04-16 |
Цены розничные, без НДС (5 %). Для компаний — персональные цены по договору: чем больше объем, тем ниже цена.Узнать свою цену
Цены со скидкой по ссылке партнера, без НДС (5 %). Зарегистрироваться
Цены со скидкой вашей компании, без НДС (5 %).Ваши условия
Быстрый старт
curl https://router.nodul.ru/api/v1/chat/completions \ -H "Authorization: Bearer $NODUL_ROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "global-3/qwen3.6-flash-2026-04-16", "messages": [{"role":"user","content":"Hello!"}] }'
import os from openai import OpenAI client = OpenAI( base_url="https://router.nodul.ru/api/v1", api_key=os.environ["NODUL_ROUTER_API_KEY"], ) response = client.chat.completions.create( model="global-3/qwen3.6-flash-2026-04-16", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content) print("cost, PnP:", response.usage.model_extra.get("cost"))
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://router.nodul.ru/api/v1", apiKey: process.env.NODUL_ROUTER_API_KEY, }); const response = await client.chat.completions.create({ model: "global-3/qwen3.6-flash-2026-04-16", messages: [{ role: "user", content: "Hello!" }], }); console.log(response.choices[0].message.content); console.log("cost, PnP:", response.usage?.cost);
package main import ( "bytes" "encoding/json" "fmt" "net/http" "os" ) func main() { body := []byte(`{"model":"global-3/qwen3.6-flash-2026-04-16","messages":[{"role":"user","content":"Hello!"}]}`) req, _ := http.NewRequest("POST", "https://router.nodul.ru/api/v1/chat/completions", bytes.NewReader(body)) req.Header.Set("Authorization", "Bearer "+os.Getenv("NODUL_ROUTER_API_KEY")) req.Header.Set("Content-Type", "application/json") resp, err := http.DefaultClient.Do(req) if err != nil { panic(err) } defer resp.Body.Close() if resp.StatusCode != http.StatusOK { var e struct{ Error struct{ Message string } } _ = json.NewDecoder(resp.Body).Decode(&e) fmt.Fprintln(os.Stderr, resp.Status, e.Error.Message) os.Exit(1) } var out struct { Choices []struct{ Message struct{ Content string } } Usage struct{ Cost json.Number } } if err := json.NewDecoder(resp.Body).Decode(&out); err != nil { panic(err) } fmt.Println(out.Choices[0].Message.Content) fmt.Println("cost, PnP:", out.Usage.Cost) }
<?php $body = '{"model":"global-3/qwen3.6-flash-2026-04-16","messages":[{"role":"user","content":"Hello!"}]}'; $ch = curl_init('https://router.nodul.ru/api/v1/chat/completions'); curl_setopt_array($ch, [ CURLOPT_POST => true, CURLOPT_HTTPHEADER => [ 'Authorization: Bearer ' . getenv('NODUL_ROUTER_API_KEY'), 'Content-Type: application/json', ], CURLOPT_POSTFIELDS => $body, CURLOPT_RETURNTRANSFER => true, ]); $response = json_decode(curl_exec($ch), true); if (curl_getinfo($ch, CURLINFO_HTTP_CODE) !== 200) { fwrite(STDERR, $response['error']['message'] ?? 'request failed'); exit(1); } echo $response['choices'][0]['message']['content'], PHP_EOL; echo 'cost, PnP: ', $response['usage']['cost'], PHP_EOL;
Описание
Описание от разработчика модели (на английском):
The Qwen3.6 native vision-language Flash model series delivers a significant performance boost over the 3.5-Flash version. This model particularly excels in agentic coding capabilities, substantially outperforming its predecessor on multiple code-agent benchmarks, as well as in mathematical and code reasoning. In terms of vision, it features markedly improved spatial intelligence, with especially notable enhancements in object localization and object detection.This release is based on a snapshot taken on April 16, 2026.
Все параметры API · 19
frequency_penaltyinclude_reasoninglogprobsmax_tokensnparallel_tool_callspresence_penaltyreasoningreasoning_effortresponse_formatseedstopstreamstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

