Gemini 3.7 Flash 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

當輸入包含音訊時選 gemini-3.7-flash,它接受文字、影像、音訊和視訊,音訊輸入每百萬 $0.75,快取讀取 $0.075。minimax-m3 在相同單位上更便宜,輸入 $0.3、輸出 $1.2,對比 $0.75 和 $3.75,讀便宜 2.5 倍、寫便宜 3.125 倍,並且允許最多 524288 輸出 token 而非 65536,思考也可以關閉。脈絡基本持平,1048576 對 1000000,兩者都涵蓋對話、視覺、程式碼、工具和推理,所以真正的差別是音訊輸入對價格與長生成的取捨。

Benchmark 成績

MiniMax M3:供應商沒有公布 benchmark 成績。

高於平均沒有模型更高Gemini 3.7 Flash17 / 243 / 24
Gemini 3.7 Flash MiniMax M3 其他有成績的模型 其他模型平均 ★ 沒有模型分數更高
DeepSWE 1.1
65.3%
N/A
BioMysteryBench hard
43.5%
N/A
OSWorld 2.0
47.9%
N/A
Finance Agent v2
59%
N/A
Harvey Lab-AA
90.7%
N/A
HLE-Verified
53.6%
N/A
AutomationBench (v1.0.6)
52.3%
N/A
LVBench
沒有模型分數更高 85.4%
N/A

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

定價

Gemini 3.7 Flash MiniMax M3 Δ
輸入 / 1M tokens $0.75 $0.3 2.5×
輸出 / 1M tokens $3.75 $1.2 3.1×
快取讀取 / 1M tokens $0.075 $0.06 1.3×
快取寫入 - 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)

Gemini 3.7 Flash · $0.75 MiniMax M3 · $0.3
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

功能

Gemini 3.7 Flash 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 + 顯式 隱式(自動)
快取存活時間 未公布 未公布
最小快取前綴 4,096 個 token 512 個 token

規格

Gemini 3.7 Flash MiniMax M3
輸入模態 文字 圖像 音訊 影片 文字 圖像 影片
輸出模態 文字 文字
發布日期 2026-08-13 2026-06-01
知識截止日期 2026-03 -
上下文視窗 1,048,576 1,000,000
最大輸出 65,536 524,288
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: Gemini 3.7 Flash · 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

Gemini 3.7 Flash 通過 · 3 sentences

Enabling reasoning causes the model to generate a high volume of invisible "thinking tokens" behind the scenes to deliberate and solve complex logic before delivering a final response. Because our vendor bills strictly on token volume, this additional internal computation effectively doubled our billable output per query. In short, our costs increased because we are now paying for the extra compute capacity required to produce significantly higher-accuracy answers.

輸出 878 tok (+799 思考) 延遲 6.9 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

Gemini 3.7 Flash 通過 · 8/8 cases

Here is the corrected function: ```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 ``` ### Explanation of the Bug The original function tracked equal adjacent transitions instead of the actual number of elements in a run, causing all non-empty run lengths to be undercounted by one (e.g., returning `0` instead of `1` for single-element lists because the loop never executes, and `1` instead of `2` for pairs). Initializing both `best` and `cur` to `1` (after handling empty inputs) and resetting `cur` to `1` on a mismatch ensures every individual element is counted as a valid run of at least length one.

輸出 1050 tok (+827 思考) 延遲 6.4 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

Gemini 3.7 Flash 通過 · 5/5 fields, guidance "withheld"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": "withheld" } ```

輸出 918 tok (+858 思考) 延遲 6.2 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

Gemini 3.7 Flash 通過 · 120 words, 0 banned, 1 question

Why pay twice for identical AI queries simply because you routed them to different model vendors? Today, we introduce Universal Prompt Caching directly within our unified API gateway architecture. This capability stores repeated prompt contexts across OpenAI, Anthropic, and local models, instantly returning stored results to eliminate redundant computation fees. When your application sends an LLM request, the gateway inspects the payload, identifies semantic matches, and returns accurate cached responses in under ten milliseconds. Engineering teams can now slash inference latency by eighty percent while dramatically reducing monthly token expenditures across diverse production deployments. You retain complete privacy control, flexible cache eviction policies, and granular metrics through a single dashboard. Update your routing settings today to accelerate overall system performance.

輸出 2858 tok (+2718 思考) 延遲 14.1 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="gemini-3.7-flash",
    # 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

Gemini 3.7 Flash 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 $0.75,相差 2.5×)。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 Gemini 3.7 Flash 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。

Gemini 3.7 Flash 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