🎁 新人 免费注册,送 10 次调用,最高 $1,免绑卡。

DeepSeek V4 Pro (0813) vs Gemini 3.6 Flash

vs

何时使用哪一个 — 经过整理的结论,而非基准测试表格

请选择 deepseek-v4-pro-0813 进行大批量的纯文本推理工作:它将推理作为一项显式能力,每百万 token 的输入成本为 $1.32,输出为 $3.96(在输出上比 $7.5 的 gemini-3.6-flash 大约便宜 1.9x),并允许高达 393216 个输出 token,约为 Google 模型 65536 上限的 6x。当输入不只是文本时请选择 gemini-3.6-flash——它在文本之外还接受图像、视频和音频并增加了视觉能力,音频输入按每百万音频 token $5 计费。上下文在 1000000 与 1048576 token 的对比中实际上不相上下;请注意,在 gemini-3.6-flash 上无法禁用 thinking。

定价

DeepSeek V4 Pro (0813) Gemini 3.6 Flash Δ
输入 / 1M tokens $1.32 $1.5 0.88×
输出 / 1M tokens $3.96 $7.5 0.53×
缓存读取 / 1M tokens $0.132 $0.15 0.88×
缓存写入 不单独收费

费率取自构建时的实时目录;每个模型页面均附有当前的费率卡。

它们的位置 — 以该计费单位计费的所有 63 个 聊天 模型的 每 1M token 的输入价格(对数刻度)

能力

DeepSeek V4 Pro (0813) Gemini 3.6 Flash
工具使用
思考控制 始终开启 始终开启
结构化输出
提示词缓存 隐式(自动) 隐式 + 显式
缓存生存时间 no fixed TTL (evicted when unused) 未公开
最小缓存前缀 未公开 4096 个 token

规格

DeepSeek V4 Pro (0813) Gemini 3.6 Flash
输入模态 文本 文本 图像 音频 视频
输出模态 文本 文本
发布日期 2026-08-13
知识截止日期 2026-03
上下文窗口 1M 1M
最大输出 393K 66K
思考参数 reasoning_effort thinkingLevel
允许的值
reasoning_effort
  • the model card documents low
  • high
  • max
  • minimal
  • low
  • medium
  • high
默认值 medium

规格转录自各供应商的文档;若供应商未发布某项数据,则直接省略该行,而非进行推断。 完整来源: DeepSeek V4 Pro (0813) · Gemini 3.6 Flash

单个 Prompt,两个模型 —— 通过网关实测

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

DeepSeek V4 Pro (0813) 通过 · 3 sentences

Enabling reasoning causes the model to generate a hidden chain-of-thought with many additional tokens before producing the final answer, which sharply increases compute consumption per request. Those extra reasoning tokens are billed at the same or higher rates, so total usage doubled even though the volume of final outputs stayed similar. We can control this by adjusting reasoning effort, setting token limits, or routing only complex requests through reasoning mode.

输出 308 tok (+226 思考) 延迟 5.1 s

Gemini 3.6 Flash 通过 · 3 sentences

Enabling reasoning causes the model to generate thousands of internal "thinking" tokens behind the scenes to process logic before delivering the final response. Because our vendor bills us for every token generated—including these intermediate processing steps—our billable output volume per query surged significantly. Since output tokens carry a much higher unit cost than input tokens, this jump in processing volume directly doubled our overall spend.

输出 893 tok (+816 思考) 延迟 4.7 s

指令遵循(恰好三句,可数)、受众适配(面向 CFO 的语气),以及下方 token 计量所暴露的隐藏思考计费缺口。

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

DeepSeek V4 Pro (0813) 通过 · 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 `cur` was initialized to `0` and only counted adjacent matching pairs, so a run of length `n` produced `n - 1` (or `0` for a single element) instead of `n`. The code also reset to `0` on a change, when the new run should start at length `1`. Initializing `cur` and `best` to `1` fixes both the single-element case and runs ending at the last index.

输出 1315 tok (+1130 思考) 延迟 16.9 s

Gemini 3.6 Flash 通过 · 8/8 cases

Here is the fixed function along with an explanation of the bugs: ```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 The original function initialized `cur` and `best` to `0` and incremented `cur` on matching adjacent items, which meant it was counting identical adjacent *pairs* rather than the total number of *elements* in a run. This caused single-element inputs to skip the loop and return `0` instead of `1`, and undercounted all run lengths by 1 (for example, a run of two items at the end of the list resulted in `cur = 1`). […]

输出 2034 tok (+1768 思考) 延迟 10.0 s

修复是否真的正确(可运行)、解释的信息密度,以及在一个边界明确的任务上的 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,schema 精确

DeepSeek V4 Pro (0813) 通过 · 5/5 fields, guidance null

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11.0,"guidance":null}

输出 2155 tok (+2121 思考) 延迟 26.0 s

Gemini 3.6 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 2843 tok (+2783 思考) 延迟 13.1 s

schema 服从度(不臆造字段)、幻觉压力(guidance 明确被暂缓给出),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

DeepSeek V4 Pro (0813) 通过 · 121 words, 0 banned, 1 question

Introducing cross-provider prompt caching in our API gateway. Send a prompt once, and the gateway stores its computed prefix across Anthropic, OpenAI, and other LLM providers. Subsequent requests with the same prompt hit the cache, cutting latency and token costs while keeping outputs consistent across routing decisions and provider failovers. Teams can route identical prompts between providers without reprocessing shared context or lengthy system instructions. How much could you save on repeated prompt prefixes? The cache respects provider-specific key formats, handles TTLs automatically, and works with streaming and batch requests. Enable it with one configuration flag—no changes to your application code. Available today on all plans. Monitor cache hit rates, token savings, and provider-specific performance metrics in the live dashboard.

输出 2845 tok (+2694 思考) 延迟 25.5 s

Gemini 3.6 Flash 未命中 · 60 words, 0 banned, 0 questions

72: reducing 73: your 74: monthly 75: token 76: spend. S6 (21): 77: You 78: can 79: easily 80: set 81: custom 82: expiration 83: rules, 84: configure 85: TTL 86: settings, 87: and 88: manage 89: cache 90: invalidation 91: across 92: all 93: vendors 94: from 95: one 96: centralized 97: dashboard. S7 (23): 98: Start 99: optimizing […]

输出 4092 tok (+3929 思考) 延迟 16.3 s

约束服从度(字数预算、禁用词表、唯一的那句问句)、文风指纹,以及长度控制。

只需一行代码即可在它们之间切换

两个 ID 都包含在下方的每个选项卡中 — 高亮显示的两行是唯一的修改。相同的端点,相同的密钥,相同的请求结构。

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-0813",
    # model="gemini-3.6-flash",  # 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 密钥 →

常见问题

DeepSeek V4 Pro (0813) 和 Gemini 3.6 Flash 哪个更便宜?

在 输入 / 1m tokens 方面,DeepSeek V4 Pro (0813) 更便宜($1.32 对比 $1.5,相差 1.1×)。其他行可能得出相反的结论——上方表格提供了完整信息,实际成本取决于你的组合使用情况。

我可以在不进行两次集成的情况下,对 DeepSeek V4 Pro (0813) 和 Gemini 3.6 Flash 进行 A/B 测试吗?

可以。两者均通过同一个兼容 OpenAI 的端点提供服务,并使用同一把 API 密钥——切换只需更改一行模型字符串,因此你可以将一部分流量路由到各个模型并直接比较账单。

DeepSeek V4 Pro (0813) 和 Gemini 3.6 Flash 支持提示词缓存吗?

是的 —— 两者对缓存读取的计费均低于其输入费率,因此热前缀工作负载的成本低于标价。准确的缓存读取行位于上方的定价表中。

相关对比

来自我们的实测研究