DeepSeek V4 Pro (0813) vs Kimi K3

Q: DeepSeek V4 Pro (0813) 和 Kimi K3 哪個比較便宜？

DeepSeek V4 Pro (0813) 在 輸入 / 1m tokens 上較便宜（$1.32 對比 $3，相差 2.3×）。其他項目可能呈現相反結果 — 上表提供完整資訊，實際成本取決於您的使用組合。

更換任一側 vs

何時該用哪一個 — 綜合評斷，而非基準測試數據表

兩者皆為文字輸出的推理模型，具備聊天、程式碼與工具使用功能，且擁有約百萬 token 的上下文，因此差異在於價格對比輸入：deepseek-v4-pro-0813 執行每百萬輸入為 $1.32、輸出為 $3.96，而 kimi-k3 為 $3 與 $15，在輸入方面便宜約 2.3x，輸出則便宜 3.8x，快取讀取為 $0.132 對比 $0.3。當您需要圖片或影片輸入，或者單一回應超過 393,216 個 token 並高達其 1,048,576 的最大輸出時，請選擇 kimi-k3。選擇 deepseek-v4-pro-0813 進行大量的純文字工作，並請注意 kimi-k3 無法關閉 thinking。

定價

	DeepSeek V4 Pro (0813)	Kimi K3	Δ
輸入 / 1M tokens	$1.32	$3	0.44×
輸出 / 1M tokens	$3.96	$15	0.26×
快取讀取 / 1M tokens	$0.132	$0.3	0.44×
快取寫入	不額外計費	—	—

費率取自建置時的即時目錄；各模型頁面皆附有目前的費率卡。

它們的相對位置 — 在此計費單位下，所有 63 個聊天模型的每 1M tokens 的輸入價格（對數尺度）

DeepSeek V4 Pro (0813) · $1.32 Kimi K3 · $3

$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

	DeepSeek V4 Pro (0813)	Kimi K3
工具使用	是	是
思考控制	常駐開啟	常駐開啟
結構化輸出	是	是
提示快取	隱式（自動）	隱式（自動）
快取生命週期	no fixed TTL (evicted when unused)	未公開
最小快取前綴	未公開	未公開

規格

	DeepSeek V4 Pro (0813)	Kimi K3
輸入模態	文字	文字影像影片
輸出模態	文字	文字
發布日期	2026-08-13	—
上下文視窗	1M	1M
最大輸出	393K	1M
思考參數	reasoning_effort	reasoning_effort (top-level; the thinking object is not accepted)
可接受的值	reasoning_effort the model card documents low high max	reasoning_effort low high max
預設值	—	max

規格摘錄自各供應商的文件；供應商未發布的資料列會直接省略，而非自行推測。完整來源： DeepSeek V4 Pro (0813) · Kimi K3

單一提示詞，兩款模型 — 經由閘道測量

針對 CFO 的推論修復包含錯誤的函式擷取至 schema 依照限制條件撰寫

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 (0813) 通過 · 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.

輸出 308 tok (+226 思考) 延遲 5.1 s

Kimi K3 通過 · 3 sentences

Reasoning models don't just answer questions—they "think" first, generating long internal chains of step-by-step logic before producing a response. Those hidden thinking steps are billed as output tokens (the most expensive kind, typically 3–5x the price of input tokens), and a single query can generate thousands of them even when the visible answer is only a paragraph long. So you're paying for dramatically more compute per request: the bill doubled because the model does far more work behind the scenes, not because usage increased.

輸出 755 tok (+637 思考) 延遲 20.8 s

指令遵循（恰好三句，可數）、受眾適配（面向 CFO 的語氣），以及下方 token 計量所暴露的隱藏思考計費缺口。

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. 檢查修復通過測試

DeepSeek V4 Pro (0813) 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 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.

輸出 1315 tok (+1130 思考) 延遲 16.9 s

Kimi K3 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 a fencepost error: `cur` counts *matching adjacent pairs* rather than *items in the run*, because it starts at 0 and only increments when `xs[i] == xs[i - 1]`. A run of length L contains L−1 equal pairs, so every run was undercounted by exactly one. For a single-element list (a run of length 1) the loop never runs and the function returns 0 instead of 1; likewise any run ending at the last index — e.g. the two `2`s in `[1, 2, 2]` — reported 1 instead of 2, making it look like no run existed at all. […]

輸出 1837 tok (+1547 思考) 延遲 47.2 s

修復是否真的正確（可執行）、解釋的資訊密度，以及在一個邊界明確的任務上的 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. 檢查合法 JSON，schema 精確

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

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

輸出 2155 tok (+2121 思考) 延遲 26.0 s

Kimi K3 通過 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }

輸出 924 tok (+863 思考) 延遲 25.9 s

schema 服從度（不臆造欄位）、幻覺壓力（guidance 明確被暫緩給出），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 (0813) 通過 · 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.

輸出 2845 tok (+2694 思考) 延遲 25.5 s

Kimi K3 通過 · 120 words, 0 banned, 1 question

Meet Prompt Cache, a new API gateway capability that stores prompt responses and serves them across OpenAI, Anthropic, Google, and Azure endpoints. It matches requests by model, prompt hash, tools, temperature, and tenant policy, so repeated work returns fast while sensitive contexts stay isolated. Teams set TTLs, stale rules, encryption scopes, and bypass flags per route. Analytics show hit rate, latency saved, token spend avoided, and drift risk by provider. What changes for developers? Keep one integration, add cache headers, and watch fallback logic respect consent, residency, and audit needs. During rollout, canary keys compare fresh answers with cached copies before promotion. Prompt Cache cuts vendor calls, steadies p95 latency, and gives platform owners controls for cost, quality, and compliance.

輸出 1527 tok (+1354 思考) 延遲 37.9 s

約束服從度（字數預算、禁用詞表、唯一的那句問句）、文風指紋，以及長度控制。

只需一行程式碼即可在兩者間切換

以下每個頁籤中都有這兩個 ID — 醒目提示的這兩行是唯一的修改處。相同的端點，相同的金鑰，相同的請求結構。

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-k3",  # 取消註解此行，並註解上一行
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://synthorai.io/v1",
  apiKey: "sk-syn-...",
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4-pro-0813",
  // model: "kimi-k3",  // 取消註解此行，並註解上一行
  messages: [{ role: "user", content: "Summarize this diff" }],
  reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);

curl https://synthorai.io/v1/chat/completions \
  -H "Authorization: Bearer sk-syn-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro-0813",
    # "model": "kimi-k3",  # 取消註解此行，並註解上一行
    "messages": [{"role": "user", "content": "Hello"}],
    "reasoning_effort": "medium"
  }'

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://synthorai.io/v1"),
		option.WithAPIKey("sk-syn-..."),
	)
	resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
		Model: "deepseek-v4-pro-0813",
		// Model: "kimi-k3",  // 取消註解此行，並註解上一行
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("Summarize this diff"),
		},
		ReasoningEffort: openai.ReasoningEffortMedium,
	})
	fmt.Println(resp.Choices[0].Message.Content)
}

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://synthorai.io/v1")
    .apiKey("sk-syn-...")
    .build();

ChatCompletion resp = client.chat().completions().create(
    ChatCompletionCreateParams.builder()
        .model("deepseek-v4-pro-0813")
        // .model("kimi-k3")  // 取消註解此行，並註解上一行
        .addUserMessage("Summarize this diff")
        .reasoningEffort(ReasoningEffort.MEDIUM)
        .build());
System.out.println(resp.choices().get(0).message().content().orElse(""));

取得 API 金鑰 →

常見問題

DeepSeek V4 Pro (0813) 和 Kimi K3 哪個比較便宜？

DeepSeek V4 Pro (0813) 在輸入 / 1m tokens 上較便宜（$1.32 對比 $3，相差 2.3×）。其他項目可能呈現相反結果 — 上表提供完整資訊，實際成本取決於您的使用組合。

我可以在不進行兩次整合的情況下，對 DeepSeek V4 Pro (0813) 和 Kimi K3 進行 A/B 測試嗎？

可以。兩者皆透過同一個相容 OpenAI 的端點提供服務，並使用同一把 API 金鑰 — 切換只需更改一行的模型字串，因此您可以將部分流量分別導向兩者並直接比較帳單。

DeepSeek V4 Pro (0813) 與 Kimi K3 支援提示快取嗎？

是的 — 兩者的快取讀取費率皆低於其輸入費率，因此具有暖前綴的工作負載成本會低於牌價所示。確切的快取讀取列請見上方的定價表。

定價

能力

規格

單一提示詞，兩款模型 — 經由閘道測量

只需一行程式碼即可在兩者間切換

常見問題

相關比較