Gemini 3.7 Flash vs MiniMax M3

MiniMax M3 已从我们的目录下线。下方是它最后公布的价格;这个模型已无法调用,对比中的另一个模型仍可正常调用。

vs

什么时候选哪个

当输入包含音频时选 gemini-3.7-flash,它接受文本、图像、音频和视频,音频输入每百万 $0.75,缓存读取 $0.075。minimax-m3 在相同单位上更便宜,输入 $0.3、输出 $1.2,对比 $0.75 和 $3.75,读便宜 2.5 倍、写便宜 3.125 倍,并且允许最多 524288 输出 token 而非 65536,思考也可以关闭。上下文基本持平,1048576 对 1000000,两者都覆盖对话、视觉、代码、工具和推理,所以真正的差别是音频输入对价格与长生成的取舍。

Benchmark 成绩

MiniMax M3:供应商没有公布 benchmark 成绩。

高于同类均值无更高分Gemini 3.7 Flash17 / 243 / 24
Gemini 3.7 Flash MiniMax M3 其他参测模型 同类均值 ★ 没有模型得分更高
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
没有模型得分更高 85.4%
N/A

供应商公布: 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

价格

Gemini 3.7 Flash MiniMax M3 Δ
输入 / 1M token $0.75 $0.3 2.5×
输出 / 1M token $3.75 $1.2 3.1×
缓存读取 / 1M token $0.075 $0.06 1.3×
缓存写入 - 不单独收费 -

价格取自构建时的实时目录,最新价格见各模型页面。

两个模型所处的位置:全部 91 个按同一单位计费的聊天模型的每 1M token 输入价分布(对数刻度)

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

能力

Gemini 3.7 Flash MiniMax M3
工具调用 是 是
思考控制 是,但供应商未公布调节参数 可配置
结构化输出 是 -
提示词缓存 隐式 + 显式 隐式(自动)
缓存有效期 未公布 未公布
最小缓存前缀 4,096 个 token 512 个 token

规格

Gemini 3.7 Flash MiniMax M3
输入模态 文本 图像 音频 视频 文本 图像 视频
输出模态 文本 文本
发布日期 2026-08-13 2026-06-01
知识截止日期 2026-03 -
上下文窗口 1,048,576 1,000,000
最大输出 65,536 524,288
思考参数 -
  • thinking.type
  • reasoning_split
可选值 -
thinking.type
  • adaptive
  • disabled
reasoning_split
  • boolean
默认值 - adaptive:思考开启,由模型判断何时需要额外推理

规格照录自各供应商的文档;供应商没有公布的项目,对应的行直接省略,不做推断。 完整来源: Gemini 3.7 Flash · MiniMax M3

同一条提示词,两个模型,经网关实测

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

Gemini 3.7 Flash 通过 · 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.

输出 878 tok (+799 思考) 延迟 6.9 s

MiniMax M3 通过 · 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.

输出 764 tok (+629 思考) 延迟 3.5 s

指令遵循(恰好三句,数得出来)、受众适配(对 CFO 说话的口吻),以及下方 token 计数暴露出的隐藏思考计费差额。

提示词 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. 检查 修复通过测试

Gemini 3.7 Flash 通过 · 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.

输出 1050 tok (+827 思考) 延迟 6.4 s

MiniMax M3 通过 · 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.

输出 845 tok (+596 思考) 延迟 3.5 s

修复是否真的正确(能运行)、解释的信息密度,以及在一个范围明确的任务上的 token 效率。

提示词 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. 检查 合法 JSON,严格符合 schema

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

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

输出 918 tok (+858 思考) 延迟 6.2 s

MiniMax M3 通过 · 5/5 fields, guidance null

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

输出 1002 tok (+955 思考) 延迟 3.6 s

是否严守 schema(不臆造字段)、能否顶住幻觉压力(原文明说暂不给出 guidance),以及结构化输出路径的差异。

提示词 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. 检查 120 词,0 个禁用词

Gemini 3.7 Flash 通过 · 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.

输出 2858 tok (+2718 思考) 延迟 14.1 s

MiniMax M3 通过 · 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.

输出 2808 tok (+2656 思考) 延迟 6.0 s

是否守住约束(字数预算、禁用词表、只能有一个问句)、文风特征,以及长度控制。

改一行代码就能在两个模型之间切换

下方每个标签页里都有两个模型 ID,高亮的那两行是唯一要改的地方。端点不变,API key 不变,请求结构也不变。

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",  # 取消注释此行,注释上一行
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

获取 API key →

常见问题

Gemini 3.7 Flash 和 MiniMax M3 哪个更便宜?

按「输入 / 1M token」算,MiniMax M3 更便宜($0.3 对 $0.75,相差 2.5×)。其他计费项的结论可能相反,完整价格见上方表格,实际成本取决于你的用量构成。

不用分别集成两次,就能对 Gemini 3.7 Flash 和 MiniMax M3 做 A/B 测试吗?

可以。两个模型走同一个 OpenAI 兼容端点,用同一个 API key,切换时只要改一行里的模型名,所以可以给两个模型各分一部分流量,直接对比账单。

Gemini 3.7 Flash 和 MiniMax M3 支持提示词缓存吗?

支持。两个模型的缓存读取价都低于各自的输入价,所以前缀能反复命中缓存的负载,实际成本会比按官网价估算的低。具体的缓存读取价见上方价格表。

相关对比

我们的实测研究