DeepSeek V4 Flash (0731) vs MiniMax M3

vs

什麼情況選哪一個

deepseek-v4-flash-0731 和 minimax-m3 都是純文字輸出模型,擁有 1000000-token 的上下文,其中 minimax-m3 在新 token 上略便宜:每百萬輸入 $0.3、輸出 $1.2,對比 $0.44 和 $1.32。deepseek-v4-flash-0731 在重複使用上保持優勢,快取讀取 $0.044 對比 $0.06,大約低 1.4x,不過其 393216-token 的最大輸出低於 524288 的上限。當您需要圖像或影片輸入、更大的最大輸出或可關閉思考時,請選擇 minimax-m3。對於快取前綴佔帳單大宗的純文字聊天、程式碼與推理工作,請選擇 deepseek-v4-flash-0731。

Benchmark 成績

MiniMax M3:供應商沒有公布 benchmark 成績。

高於平均DeepSeek V4 Flash (0731)10 / 28
DeepSeek V4 Flash (0731) 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
56%
N/A
Cybergym
76.7%
N/A
JobBench
41.3%
N/A
GPQA Diamond
89.9%
N/A
Agents' Last Exam
25.2%
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 ByteDance DeepSeek DeepSeek Google Google Google Google MiniMax Moonshot OpenAI OpenAI OpenAI OpenAI OpenAI Tencent Z.ai Z.ai Z.ai Z.ai

定價

DeepSeek V4 Flash (0731) MiniMax M3 Δ
輸入 / 1M tokens $0.44 $0.3 1.5×
輸出 / 1M tokens $1.32 $1.2 1.1×
快取讀取 / 1M tokens $0.044 $0.06 0.73×
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 86 個聊天模型(對數尺度)

功能

DeepSeek V4 Flash (0731) MiniMax M3
工具使用 是 是
思考控制 是,但供應商未公布調整參數 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 Flash (0731) 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 2026-07-31 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_split
可接受的值 -
thinking.type
  • adaptive
  • disabled
reasoning_split
  • boolean
預設值 - 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 Flash (0731) · 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 Flash (0731) 通過 · 3 sentences

Enabling reasoning mode prompts the model to generate extensive internal chain-of-thought tokens before answering, often multiplying total token output per query by several times. This directly inflates costs because we are billed per token, and these reasoning tokens are processed at a premium compute tier that carries a higher price per million tokens. However, this spend buys measurably higher accuracy and fewer failed calls, so we are tracking it against specific error-reduction KPIs to ensure the ROI justifies the increase.

輸出 365 tok (+266 思考) 延遲 5.1 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 Flash (0731) 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 ``` The original bug stems from initializing `cur` to 0 and only incrementing it when adjacent elements are equal, which counts the number of *equal transitions* rather than the actual run length—so every run of length L is reported as L−1, and a single‑element run (with no transitions) yields 0. Moreover, because `best` is updated only inside the equality branch, it never accounts for a run that ends at the last element if that run is longer than any previously seen (though the real issue remains the off‑by‑one). […]

輸出 1268 tok (+1016 思考) 延遲 14.0 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 Flash (0731) 通過 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": null, "guidance": null }

輸出 1119 tok (+1072 思考) 延遲 12.3 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 Flash (0731) 未通過 · 141 words, 0 banned, 1 question

**Introducing Prompt Cache for API Gateway** We are pleased to announce Prompt Cache, a new feature that stores and reuses identical prompt prefixes across all connected LLM providers. By automatically recognizing repeated requests, this cache reduces token consumption and lowers latency without altering your application logic. Whether you use OpenAI, Anthropic, or open-source models, the cache operates transparently, ensuring consistent behavior while cutting costs. Developers can configure cache TTL and scoping rules via a simple API call, giving you precise control over data freshness and privacy. This feature also minimizes redundant upstream calls, freeing provider rate limits for more critical workloads. Start caching today through the dashboard or CLI, and watch your operational expenses drop significantly. […]

輸出 254 tok (+80 思考) 延遲 4.4 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-flash-0731",
    # 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 Flash (0731) 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 $0.44,相差 1.5×)。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 Flash (0731) 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 Flash (0731) 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