DeepSeek V4 Pro vs MiniMax M3

MiniMax M3 已從我們的目錄下架。下方是它最後公布的費率;它已經無法呼叫,這組比較裡的另一個模型則仍可呼叫。

vs

什麼情況選哪一個

兩者都有 1000000 token 上下文,涵蓋對話、程式碼、推理與工具呼叫,思考都可關閉,所以決定因素是價格與輸入類型。minimax-m3 在每一檔公開費率上都更便宜——每百萬輸入 $0.3 對 $1.32,輸出 $1.2 對 $3.96,快取讀取 $0.06 對 $0.132——而且除文字外還接受影像與影片,單次最多輸出 524288 token(對方 393216)。它已從我們的目錄下架,所以兩者中能呼叫的是 deepseek-v4-pro;純文字工作按現價選它。

Benchmark 成績

MiniMax M3:供應商沒有公布 benchmark 成績。

高於平均DeepSeek V4 Pro5 / 10
DeepSeek V4 Pro MiniMax M3 其他有成績的模型 其他模型平均 ★ 沒有模型分數更高
SWE-Bench Pro
59%
N/A
CoWorkBench max
66.3%
N/A
Humanity's Last Exam no tools
37.7%
N/A
MCP-Mark
57.1%
N/A

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

定價

DeepSeek V4 Pro MiniMax M3 Δ
輸入 / 1M tokens $1.32 $0.3 4.4×
輸出 / 1M tokens $3.96 $1.2 3.3×
快取讀取 / 1M tokens $0.132 $0.06 2.2×
快取寫入 不額外計費 不額外計費 -

費率取自網站建置時的即時目錄;各模型頁面都列有最新的價目。

兩者的相對位置:每 1M tokens 的輸入價格,涵蓋同一計費單位下全部 91 個聊天模型(對數尺度)

DeepSeek V4 Pro · $1.32 MiniMax M3 · $0.3
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

功能

DeepSeek V4 Pro MiniMax M3
工具使用 是 是
思考控制 可設定 可設定
結構化輸出 是 -
提示詞快取 隱式(自動) 隱式(自動)
快取存活時間 no fixed TTL (evicted when unused) 未公布
最小快取前綴 未公布 512 個 token

規格

DeepSeek V4 Pro MiniMax M3
輸入模態 文字 文字 圖像 影片
輸出模態 文字 文字
發布日期 2026-04-24 2026-06-01
上下文視窗 1,000,000 1,000,000
最大輸出 393,216 524,288
思考參數
  • thinking.type
  • reasoning_effort
  • thinking.type
  • reasoning_split
可接受的值
thinking.type
  • enabled
  • disabled
reasoning_effort
  • high
  • max (low and medium map to high, xhigh maps to max)
thinking.type
  • adaptive
  • disabled
reasoning_split
  • boolean
預設值 enabled,reasoning_effort 為 high;部分複雜的智慧體請求會自動設為 max 自適應:思考開啟,由模型判斷何時需要額外推理

規格摘錄自各供應商的文件;供應商沒有公布的項目就直接略過,不自行推測。 完整來源: DeepSeek V4 Pro · MiniMax M3

同一段提示詞,兩個模型,經閘道實測

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

DeepSeek V4 Pro 通過 · 3 sentences

Enabling reasoning causes the model to generate a lengthy internal chain‑of‑thought before it delivers a visible answer, and we are billed for every one of those hidden reasoning tokens just as we are for the final output. In most interactions, the volume of these unseen tokens at least equals the visible response, effectively doubling the total tokens consumed per query. That doubled token consumption translates directly into a doubled per‑query cost, which is why our overall LLM bill doubled.

輸出 641 tok (+545 思考) 延遲 11.5 s

MiniMax M3 通過 · 3 sentences

Reasoning models don't just answer — they first generate extensive internal "thinking" tokens to work through the problem step-by-step, and you're billed for all of those tokens even though users never see them. A query that previously cost ~200 tokens may now cost 2,000–10,000 once reasoning is enabled, multiplying per-query spend by roughly 5–50x while the visible output stayed the same size — that's the doubling. The lever is tuning: cap reasoning effort on simple queries, cache the reasoning traces, and reserve the full reasoning model for only your hardest 10–20% of requests, which typically restores 60–80% of the savings.

輸出 764 tok (+629 思考) 延遲 3.5 s

是否照指令做(剛好三句,數得出來)、語氣是否貼合對象(寫給 CFO 看),以及下方 token 計量顯示出的隱藏思考計費落差。

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 修正後通過測試

DeepSeek V4 Pro 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 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The bug stems from initializing `cur = 0` and only incrementing it when two adjacent elements match, which counts the number of *additional* equal elements rather than the actual run length (which is `cur + 1`). As a result, the returned `best` is always one less than the true longest run—most obviously returning 0 for a single-element list instead of 1. […]

輸出 2418 tok (+2131 思考) 延遲 35.6 s

MiniMax M3 通過 · 8/8 cases

The bug is that the loop starts at index 1 and treats `cur` as the number of *equal transitions* rather than the run length, so a run of *k* consecutive equal items is reported as `k − 1`, and a single-element list (where the loop body never executes) returns 0 instead of 1. A correct version tracks the actual run length by seeding `cur = 1` and resetting it to 1 (not 0) on a mismatch: ```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 if cur > best: best = cur return best ``` Now `[5]` returns `1`, `[1,1,1]` returns `3`, and a run like `[1,2,2,2]` that ends at the last index is correctly captured as `3` because `cur` is updated before `best` is compared on every iteration, including the final one.

輸出 845 tok (+596 思考) 延遲 3.5 s

修正是否真的正確(跑得起來)、說明的資訊密度,以及在範圍明確的任務上的 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 有效的 JSON,完全符合 schema

DeepSeek V4 Pro 通過 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": "eleven and change", "guidance": null }

輸出 1204 tok (+1153 思考) 延遲 19.9 s

MiniMax M3 通過 · 5/5 fields, guidance null

```json { "company": null, "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": null, "guidance": null } ```

輸出 1002 tok (+955 思考) 延遲 3.6 s

是否遵守 schema(不自創欄位)、面對幻覺誘因的表現(題目明確不給 guidance),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

DeepSeek V4 Pro 沒有可評分的回答 · no answer text within 16,384 tokens (all of it went to thinking)

模型沒有回傳任何回答文字,token 額度全都用在隱藏的思考上了。

輸出 8193 tok (+8192 思考) 延遲 106.2 s

MiniMax M3 通過 · 121 words, 0 banned, 1 question

Introducing PromptCache, our intelligent caching layer for the API gateway. Tired of paying twice for identical requests? The feature stores prompt-response pairs across every connected provider, returning cached results instead of hitting costly endpoints. Deployment requires only a single configuration flag, and semantic similarity detection happens automatically. Latency drops up to 70% on repeated traffic while costs follow the same downward curve. Developers access detailed cache hit metrics, eviction logs, and provider breakdowns through the dashboard. Whether routing to OpenAI, Anthropic, or local models, every cached token saves time and money. The cache respects TTL policies, supports manual purging, and encrypts stored content. Available today for Pro and Enterprise tiers—enable PromptCache on existing endpoints and watch inference bills shrink immediately.

輸出 2808 tok (+2656 思考) 延遲 6.0 s

是否遵守限制(字數上限、禁用詞清單、只能有一句問句)、文字風格的特徵,以及長度控制。

改一行程式碼就能在兩者之間切換

下面每個頁籤都列了這兩個模型 ID,要改的只有醒目標示的那兩行。端點、金鑰和請求格式都不變。

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    # model="minimax-m3",  # 取消這一行的註解,並把上一行註解掉
    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

DeepSeek V4 Pro 和 MiniMax M3 哪個比較便宜?

以「輸入 / 1M tokens」來看,MiniMax M3 比較便宜($0.3 對 $1.32,相差 4.4×)。其他項目的結果可能相反,完整價目請看上表;實際成本要看你的用量組合。

可以只串接一次,就對 DeepSeek V4 Pro 和 MiniMax M3 做 A/B 測試嗎?

可以。兩個模型都走同一個 OpenAI 相容端點,用的也是同一把 API 金鑰,切換時只要改一行裡的模型名稱字串。你可以把一部分流量分別導到兩邊,再直接比較帳單。

DeepSeek V4 Pro 與 MiniMax M3 支援提示詞快取嗎?

支援。兩者的快取讀取費率都低於輸入費率,所以前綴已經進快取的工作負載,實際成本會比官網價算出來的低。確切的快取讀取價格請見上方定價表。

相關比較