DeepSeek V4 Pro vs Gemini 3.6 Flash
何時該用哪一個 — 綜合評斷,而非基準測試數據表
文字輸入價格接近(每百萬 $1.608 對 $1.5),所以差別在別處:deepseek-v4-pro 輸出計費 $3.216,對比 gemini-3.6-flash 的 $7.5;快取讀取 $0.0134 對 $0.15;每次回覆最多可輸出 393216 token,對比 65536。長的純文字推理和程式碼工作選 deepseek-v4-pro,在 1000000 token 視窗內思考可關閉。輸入包含影像、視訊或音訊(音訊輸入每百萬 $5),並且想要在 1048576 token 上使用視覺與工具時選 gemini-3.6-flash。
定價
| DeepSeek V4 Pro | Gemini 3.6 Flash | Δ | |
|---|---|---|---|
| 輸入 / 1M tokens | $1.608 | $1.5 | 1.1× |
| 輸出 / 1M tokens | $3.216 | $7.5 | 0.43× |
| 快取讀取 / 1M tokens | $0.0134 | $0.15 | 0.089× |
| 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)
能力
| DeepSeek V4 Pro | Gemini 3.6 Flash | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 可配置 | 常駐開啟 |
| 結構化輸出 | 是 | 是 |
| 提示快取 | 隱式(自動) | 隱式 + 顯式 |
| 快取生命週期 | no fixed TTL (evicted when unused) | 未公開 |
| 最小快取前綴 | 未公開 | 4096 個 token |
規格
| DeepSeek V4 Pro | Gemini 3.6 Flash | |
|---|---|---|
| 輸入模態 | 文字 | 文字 影像 音訊 影片 |
| 輸出模態 | 文字 | 文字 |
| 發布日期 | 2026-04-24 | — |
| 知識截止日期 | — | 2026-03 |
| 上下文視窗 | 1M | 1M |
| 最大輸出 | 393K | 66K |
| 思考參數 |
| thinkingLevel |
| 可接受的值 | thinking.type
reasoning_effort
|
|
| 預設值 | enabled, with reasoning_effort high some complex agent requests are automatically set to max | medium |
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 · Gemini 3.6 Flash
單一提示詞,兩款模型 — 經由閘道測量
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
Gemini 3.6 Flash 通過 · 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.
輸出 893 tok (+816 思考) 延遲 4.7 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。
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
Gemini 3.6 Flash 通過 · 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`). […]
輸出 2034 tok (+1768 思考) 延遲 10.0 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。
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
Gemini 3.6 Flash 通過 · 5/5 fields, guidance "withheld"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": "withheld" } ```
輸出 2843 tok (+2783 思考) 延遲 13.1 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。
DeepSeek V4 Pro 沒有可評分的回答 · no answer text within 16,384 tokens (all of it went to thinking)
模型未回傳任何回答文字——所有 token 額度皆耗費於隱藏思考。
輸出 8193 tok (+8192 思考) 延遲 106.2 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 […]
輸出 4092 tok (+3929 思考) 延遲 16.3 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",
# model="gemini-3.6-flash", # 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",
// model: "gemini-3.6-flash", // 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",
# "model": "gemini-3.6-flash", # 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",
// Model: "gemini-3.6-flash", // 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")
// .model("gemini-3.6-flash") // 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(""));常見問題
DeepSeek V4 Pro 和 Gemini 3.6 Flash 哪個比較便宜?
Gemini 3.6 Flash 在 輸入 / 1m tokens 上較便宜($1.5 對比 $1.608,相差 1.1×)。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 和 Gemini 3.6 Flash 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 與 Gemini 3.6 Flash 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。