新用戶 免費註冊,送 10 次呼叫,最高 $1,免綁卡。

Qwen3.8 Flash vs Qwen3.8 Max

vs

何時用哪一個

兩者皆為 Alibaba 模型,具備相同的能力集(對話、視覺、程式碼、推論、工具、長脈絡),且最大輸出皆為 131072,因此差異在於價格與輸入。處理大量工作請選擇 qwen3.8-flash:在輸入 $0.15 與輸出 $0.47 的情況下,其在輸入與輸出雙方面皆比輸入 $2 與輸出 $6 的 qwen3.8-max 便宜約 13x,其快取讀取為 $0.016,而後者為 $0.25,它具備 1000000 token 的脈絡相對於 983616,它也接受影片,且可停用其思考功能。當您明確需要更高階的文字與影像模型,且成本差異不是限制時,請選擇 qwen3.8-max。

Benchmark 成績

領先高於同儕均值無人分數更高Qwen3.8 Flash313 / 163 / 16Qwen3.8 Max731 / 408 / 40

雙方都被測過的 10 項。

Qwen3.8 Flash Qwen3.8 Max 其他被測模型 同儕均值 無人分數更高
SWE-Bench Pro
62.5%
67.7%
OSWorld 2.0 partial
52.3%
N/A
Cybergym
N/A
78.5%
HealthBench
N/A
無人分數更高 60.2%
JobBench
55.7%
53.4%
PLawBench
N/A
無人分數更高 73.2%
GPQA Diamond
91.7%
92.6%
ERQA
無人分數更高 72.3%
N/A
Agents' Last Exam Pass
24.3%
27%
LVBench
76.6%
N/A

廠商公布: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

定價

Qwen3.8 Flash Qwen3.8 Max Δ
輸入 / 1M tokens $0.15 $2 0.075×
輸出 / 1M tokens $0.47 $6 0.078×
快取讀取 / 1M tokens $0.016 $0.25 0.064×
快取寫入 1.25x 1.25x -

費率取自建置時的即時目錄;各模型頁面皆附有目前的費率卡。

它們的相對位置 — 在此計費單位下,所有 71 個 聊天 模型的 每 1M tokens 的輸入價格(對數尺度)

Qwen3.8 Flash · $0.15 Qwen3.8 Max · $2
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

Qwen3.8 Flash Qwen3.8 Max
工具使用
思考控制 可配置 是 —— 廠商未公布調節參數
結構化輸出
提示快取 隱式 + 顯式 隱式 + 顯式
快取生命週期 explicit: 5m, reset on hit explicit: 5m, reset on hit
最小快取前綴 1024 個 token 1024 個 token

規格

Qwen3.8 Flash Qwen3.8 Max
輸入模態 文字 影像 影片 文字 影像
輸出模態 文字 文字
發布日期 2026-08-27 2026-08-03
上下文視窗 1M 984K
最大輸出 131K 131K
思考參數
  • enable_thinking
  • thinking_budget
  • preserve_thinking
-
可接受的值
enable_thinking
  • true
  • false
thinking_budget
  • in tokens
preserve_thinking
  • true
  • false
-
預設值

on

qwen3.8-flash is hybrid thinking with thinking enabled by default, thinking_budget defaults to the 262,144-token chain maximum, and preserve_thinking is off

-

規格摘錄自各供應商的文件;供應商未發布的資料列會直接省略,而非自行推測。 完整來源: Qwen3.8 Flash · Qwen3.8 Max

單一提示詞,兩款模型 — 經由閘道測量

提示詞 Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. 檢查 恰好 3 句

Qwen3.8 Flash 通過 · 3 sentences

Enabling reasoning makes the model spend additional output tokens to plan and validate answers before responding, and those tokens are billed. It also increases compute and latency per request, so each task consumes more capacity than a non-reasoning call. As a result, billable tokens and compute roughly doubled, directly driving the higher invoice.

輸出 330 tok (+262 思考) 延遲 8.9 s

Qwen3.8 Max 通過 · 3 sentences

Enabling reasoning makes the model produce additional hidden steps before responding, and those tokens are billable. It also tends to lengthen each interaction because the model works through more possibilities before settling on an answer. Therefore, the bill doubled mainly due to higher compute and token usage per request, not necessarily because the number of requests doubled.

輸出 378 tok (+305 思考) 延遲 8.6 s

指令遵循(恰好三句,可數)、受眾適配(面向 CFO 的語氣),以及下方 token 計量所暴露的隱藏思考計費缺口。

提示詞 This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. 檢查 修復通過測試

Qwen3.8 Flash 通過 · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The bug is that the original version counts adjacent equal pairs rather than items in a run, starting both `cur` and `best` at `0`, and it resets `cur` to `0` after a mismatch, thereby discarding the first element of the new run. That makes single-element inputs return `0`, and because every run is effectively measured in “steps” between equal elements, the last element is not counted—particularly noticeable when the longest run ends at the final index.

輸出 2123 tok (+1933 思考) 延遲 43.8 s

Qwen3.8 Max 通過 · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The bug is that the original code starts `best` and `cur` at `0`, so it counts adjacent equal *transitions* rather than the number of items in the run. A run of length `n` has only `n - 1` equal-neighbor transitions, so single-element inputs return `0`, and runs that reach the end are undercounted by one. Initializing the current run to `1` for the first element, resetting it to `1` on a break, and updating `best` from that count fixes the off-by-one.

輸出 1616 tok (+1411 思考) 延遲 34.7 s

修復是否真的正確(可執行)、解釋的資訊密度,以及在一個邊界明確的任務上的 token 效率。

提示詞 Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. 檢查 合法 JSON,schema 精確

Qwen3.8 Flash 通過 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }

輸出 519 tok (+463 思考) 延遲 10.5 s

Qwen3.8 Max 通過 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }

輸出 1199 tok (+1141 思考) 延遲 24.4 s

schema 服從度(不臆造欄位)、幻覺壓力(guidance 明確被暫緩給出),以及結構化輸出路徑的差異。

提示詞 Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. 檢查 120 詞,0 個禁用詞

Qwen3.8 Flash 通過 · 120 words, 0 banned, 1 question

We are announcing prompt caching across providers in our API gateway. Store approved prompt outputs once and reuse them across supported model providers, cutting latency, cost, and duplicate token spend. The feature matches identical requests, checks validity, and returns cached results while preserving routing controls. Developers keep existing endpoints; the gateway manages storage, invalidation, and provider differences. This reduces noisy repeat calls, improves steady responses, and frees teams to focus on better agent workflows. OpenAI, Anthropic, Google, Mistral, and custom routes are supported. Cache hits appear in analytics with latency, token, and cost reductions visible. Check retention and privacy rules before enabling it. Ready to add cache controls to your gateway? Enable it in settings and watch spend drop now.

輸出 5958 tok (+5805 思考) 延遲 88.8 s

Qwen3.8 Max 通過 · 120 words, 0 banned, 1 question

Today, our API gateway adds prompt caching across major model providers. It stores prompts and responses in one fast cache layer. Teams can lower token spend, reduce latency, and repeat reliable answers. The feature supports OpenAI, Anthropic, Google, and Mistral through one configuration. You can set retention rules, scope access, and invalidate entries quickly. How does your team maintain consistent results during provider outages? Approved cached responses keep applications stable while fallback routes recover. The dashboard shows hit rates, savings, latency, and provider usage. Engineers receive audit trails for every cached prompt, enabling safer testing. Product managers can compare cost trends before and after cache adoption. Start with a small route, then safely expand caching to production traffic right now.

輸出 2744 tok (+2591 思考) 延遲 46.3 s

約束服從度(字數預算、禁用詞表、唯一的那句問句)、文風指紋,以及長度控制。

只需一行程式碼即可在兩者間切換

以下每個頁籤中都有這兩個 ID — 醒目提示的這兩行是唯一的修改處。相同的端點,相同的金鑰,相同的請求結構。

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="qwen3.8-flash",
    # model="qwen3.8-max",  # 取消註解此行,並註解上一行
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

取得 API 金鑰 →

常見問題

Qwen3.8 Flash 和 Qwen3.8 Max 哪個比較便宜?

Qwen3.8 Flash 在 輸入 / 1m tokens 上較便宜($0.15 對比 $2,相差 13×)。其他項目可能呈現相反結果 — 上表提供完整資訊,實際成本取決於您的使用組合。

我可以在不進行兩次整合的情況下,對 Qwen3.8 Flash 和 Qwen3.8 Max 進行 A/B 測試嗎?

可以。兩者皆透過同一個相容 OpenAI 的端點提供服務,並使用同一把 API 金鑰 — 切換只需更改一行的模型字串,因此您可以將部分流量分別導向兩者並直接比較帳單。

Qwen3.8 Flash 與 Qwen3.8 Max 支援提示快取嗎?

是的 — 兩者的快取讀取費率皆低於其輸入費率,因此具有暖前綴的工作負載成本會低於牌價所示。確切的快取讀取列請見上方的定價表。

相關比較