🎁 新人 免费注册,送 10 次调用,最高 $1,免绑卡。

DeepSeek V4 Pro (0813) vs Kimi K2.7 Code

vs

何时使用哪一个 — 经过整理的结论,而非基准测试表格

在处理长上下文文本工作时请选择 deepseek-v4-pro-0813:它的 1000000 token 窗口几乎是 kimi-k2.7-code 256000 窗口的 4 倍,其 393216 的最大输出是 32768 上限的 12 倍,且缓存读取价格为 $0.132 对比 $0.19,尽管其 $1.32 的输入价格大约是 B 收取的 $0.95 的 1.4 倍。当你需要 deepseek-v4-pro-0813 不支持的图像或视频输入时,或者当低廉的未缓存提示词成本比窗口大小更重要时,请选择 kimi-k2.7-code;请注意,它无法禁用 thinking。无论哪种选择,两者的输出价格都很接近,分别为 $3.96 和 $4。

定价

DeepSeek V4 Pro (0813) Kimi K2.7 Code Δ
输入 / 1M tokens $1.32 $0.95 1.4×
输出 / 1M tokens $3.96 $4 0.99×
缓存读取 / 1M tokens $0.132 $0.19 0.69×
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) Kimi K2.7 Code
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(自动)
缓存生存时间 no fixed TTL (evicted when unused) 未公开
最小缓存前缀 未公开 未公开

规格

DeepSeek V4 Pro (0813) Kimi K2.7 Code
输入模态 文本 文本 图像 视频
输出模态 文本 文本
发布日期 2026-08-13 2026-06
上下文窗口 1M 256K
最大输出 393K 33K
思考参数 reasoning_effort
  • thinking.type
  • thinking.keep
允许的值
reasoning_effort
  • the model card documents low
  • high
  • max
type
  • accepts only enabled
keep
  • accepts only all
默认值 thinking on with Preserved Thinking on

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) · Kimi K2.7 Code

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

Kimi K2.7 Code 通过 · 3 sentences

Enabling reasoning mode causes the model to generate an internal chain-of-thought before producing each answer, and that hidden reasoning text is billed like any other output. Those extra reasoning tokens typically add up to much more than the final response itself, so every API call now costs significantly more than before. Because our overall usage volume did not change, the doubled bill reflects that each query consumes roughly twice as many billable tokens.

输出 259 tok (+174 思考) 延迟 5.4 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

Kimi K2.7 Code 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 best = max(best, cur) else: cur = 1 return best ``` The bug is that the function counts *transitions* between equal neighbors instead of counting the items themselves, so a single-element list never enters the loop and returns `0` instead of `1`. Likewise, resetting `cur` to `0` on a mismatch forgets the current item that starts a new run, which causes runs that end at the last index to be undercounted. Initializing both `best` and `cur` to `1` and resetting `cur` to `1` fixes both issues.

输出 410 tok (+222 思考) 延迟 9.4 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

Kimi K2.7 Code 通过 · 5/5 fields, guidance "withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "withheld pending the Q4 close" } ```

输出 721 tok (+663 思考) 延迟 13.2 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

Kimi K2.7 Code 通过 · 120 words, 0 banned, 1 question

We're introducing Prompt Cache for our API Gateway, a new capability that stores prompt responses across multiple AI providers. By caching replies, you reduce redundant calls, lower latency, and cut costs without changing how you build. Teams using several model providers can now reuse identical prompt results instantly, keeping traffic consistent and budgets predictable. Responses are keyed by provider, model, and exact prompt, so you always get the right result. Configure TTL, hit thresholds, and eviction rules from a single dashboard. It fits into your existing routing and requires no code changes. Setup takes minutes and works with your current endpoints. Want to see how much latency and spend you can trim? Check the docs to enable Prompt Cache today.

输出 2375 tok (+2235 思考) 延迟 38.6 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="kimi-k2.7-code",  # 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 Kimi K2.7 Code 哪个更便宜?

在 输入 / 1m tokens 方面,Kimi K2.7 Code 更便宜($0.95 对比 $1.32,相差 1.4×)。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 Kimi K2.7 Code 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 Kimi K2.7 Code 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