新帳號 免費註冊,送 10 次呼叫,最高 $1,免綁卡。

DeepSeek V4 Pro vs Kimi K2.7 Code

vs

什麼情況選哪一個

做長上下文、大批量文字選 deepseek-v4-pro:1000000 token 視窗,最多 393216 輸出 token,快取讀取每百萬 $0.132 對 $0.19。輸出基本打平,$3.96 對 $4。需要圖像或影片輸入、或更便宜的攝入時選 kimi-k2.7-code,它 $0.95 的輸入比 $1.32 低約 1.4 倍,代價是 256000 上下文、32768 token 輸出上限和無法關閉的推理。兩者都涵蓋聊天、程式碼、推理和工具,所以真正的差別在模態和上下文,不在功能。

Benchmark 成績

高於平均DeepSeek V4 Pro5 / 10Kimi K2.7 Code1 / 5
DeepSeek V4 Pro Kimi K2.7 Code 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
59%
N/A
CoWorkBench max
66.3%
N/A
Humanity's Last Exam no tools
37.7%
N/A
MCP-Atlas
N/A
76%

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

定價

DeepSeek V4 Pro Kimi K2.7 Code Δ
輸入 / 1M tokens $1.32 $0.95 1.4×
輸出 / 1M tokens $3.96 $4 0.99×
快取讀取 / 1M tokens $0.132 $0.19 0.69×
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 76 個聊天模型(對數尺度)

DeepSeek V4 Pro · $1.32 Kimi K2.7 Code · $0.95
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

功能

DeepSeek V4 Pro Kimi K2.7 Code
工具使用 是 是
思考控制 可設定 一律開啟
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 未公布

規格

DeepSeek V4 Pro Kimi K2.7 Code
輸入模態 文字 文字 圖像 影片
輸出模態 文字 文字
發布日期 2026-04-24 2026-06
上下文視窗 1M 256K
最大輸出 393K 33K
思考參數
  • thinking.type
  • reasoning_effort
  • thinking.type
  • thinking.keep
可接受的值
thinking.type
  • enabled
  • disabled
reasoning_effort
  • high
  • max (low and medium map to high, xhigh maps to max)
type
  • accepts only enabled
keep
  • accepts only all
預設值

enabled, with reasoning_effort high

some complex agent requests are automatically set to max

thinking on with Preserved Thinking on

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 Pro · Kimi K2.7 Code

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 Pro 通過 · 3 sentences

Enabling reasoning causes the model to generate a lengthy internal chain‑of‑thought before it delivers a visible answer, and we are billed for every one of those hidden reasoning tokens just as we are for the final output. In most interactions, the volume of these unseen tokens at least equals the visible response, effectively doubling the total tokens consumed per query. That doubled token consumption translates directly into a doubled per‑query cost, which is why our overall LLM bill doubled.

輸出 641 tok (+545 思考) 延遲 11.5 s

Kimi K2.7 Code 通過 · 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.

輸出 259 tok (+174 思考) 延遲 5.4 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 Pro 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 ``` **Explanation:** The bug stems from initializing `cur = 0` and only incrementing it when two adjacent elements match, which counts the number of *additional* equal elements rather than the actual run length (which is `cur + 1`). As a result, the returned `best` is always one less than the true longest run—most obviously returning 0 for a single-element list instead of 1. […]

輸出 2418 tok (+2131 思考) 延遲 35.6 s

Kimi K2.7 Code 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 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.

輸出 410 tok (+222 思考) 延遲 9.4 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 Pro 通過 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": "eleven and change", "guidance": null }

輸出 1204 tok (+1153 思考) 延遲 19.9 s

Kimi K2.7 Code 通過 · 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" } ```

輸出 721 tok (+663 思考) 延遲 13.2 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 Pro 沒有可評分的回答 · no answer text within 16,384 tokens (all of it went to thinking)

模型沒有回傳任何回答文字,token 額度全都用在隱藏的思考上了。

輸出 8193 tok (+8192 思考) 延遲 106.2 s

Kimi K2.7 Code 通過 · 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.

輸出 2375 tok (+2235 思考) 延遲 38.6 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-pro",
    # model="kimi-k2.7-code",  # 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 Pro 和 Kimi K2.7 Code 哪個比較便宜?

以「輸入 / 1M tokens」來看,Kimi K2.7 Code 比較便宜($0.95 對 $1.32,相差 1.4×)。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 Pro 和 Kimi K2.7 Code 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 Pro 與 Kimi K2.7 Code 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