DeepSeek V4 Pro (0813) vs GPT-6 Sol
什麼情況選哪一個
兩者皆按每百萬 token 計費,因此比較非常直接:deepseek-v4-pro-0813 的輸入為 $1.32,輸出為 $3.96,而 gpt-6-sol 為 $2 與 $10,輸入相差約 1.5x 且輸出相差約 2.5x,並且前者允許高達 393216 個輸出 token,對手則是 128000。請選擇 deepseek-v4-pro-0813 以獲得便宜的純文字推理、寫程式及工具使用,特別是在其 1000000-token 上下文中的長篇生成任務。當您需要影像輸入、關閉思考功能的選項或稍微大一點的 1050000-token 視窗時,請選擇 gpt-6-sol。
Benchmark 成績
供應商公布: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
定價
| DeepSeek V4 Pro (0813) | GPT-6 Sol | Δ | |
|---|---|---|---|
| 輸入 / 1M tokens | $1.32 | $2 | 0.66× |
| 輸出 / 1M tokens | $3.96 | $10 | 0.4× |
| 快取讀取 / 1M tokens | $0.132 | $0.2 | 0.66× |
| 快取寫入 | 不額外計費 | 1.25x (30m) / 2.5x (12h) | - |
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 83 個聊天模型(對數尺度)
功能
| DeepSeek V4 Pro (0813) | GPT-6 Sol | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 一律開啟 | 可設定 |
| 結構化輸出 | 是 | 是 |
| 提示詞快取 | 隱式(自動) | 隱式 + 顯式 |
| 快取存活時間 | no fixed TTL (evicted when unused) | at least 30m by default, 12h option on the Responses API |
| 最小快取前綴 | 未公布 | 1,024 個 token |
規格
| DeepSeek V4 Pro (0813) | GPT-6 Sol | |
|---|---|---|
| 輸入模態 | 文字 | 文字 圖像 |
| 輸出模態 | 文字 | 文字 |
| 發布日期 | 2026-08-13 | 2026-09-22 |
| 知識截止日期 | - | 2026-04 |
| 上下文視窗 | 1M | 1.1M |
| 最大輸出 | 393K | 128K |
| 思考參數 | reasoning_effort | reasoning.effort |
| 可接受的值 | reasoning_effort
| reasoning.effort
|
| 預設值 | - | medium |
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 (0813) · GPT-6 Sol
同一段提示詞,兩個模型,經閘道實測
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
GPT-6 Sol 通過 · 3 sentences
Enabling reasoning made the model generate extra internal tokens to work through each request, and those tokens are billed even though users don’t see them. If request volume stayed roughly the same, more billed tokens per request could explain why the bill doubled. We should check the usage breakdown to confirm, then lower reasoning effort or limit it to tasks that need it.
輸出 188 tok (+111 思考) 延遲 5.0 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。
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
GPT-6 Sol 通過 · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = 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 original `cur` counted matching *adjacent pairs*, not items, so every run was one too short—including a single-element input, which returned 0. Starting each run at 1 counts its first item, and updating `best` on every iteration ensures a run that reaches the last index is included.
輸出 206 tok (+59 思考) 延遲 5.9 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。
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
GPT-6 Sol 通過 · 5/5 fields, guidance "Withheld pending the Q4 close"
{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":null,"growth_pct":null,"guidance":"Withheld pending the Q4 close"}
輸出 227 tok (+185 思考) 延遲 5.2 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。
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
GPT-6 Sol 通過 · 120 words, 0 banned, 1 question
Today, we’re introducing cross-provider prompt caching for our API gateway, helping teams reuse repeated prompt content when routing requests among supported AI providers. The gateway identifies eligible prompt prefixes, stores cache references, and applies them to subsequent requests where provider capabilities allow. Why send the same context again if it can be reused? With fewer duplicate input tokens, applications can reduce costs and improve latency without changing how developers call the gateway. Configure caching by route, monitor hit rates and savings in your dashboard, and keep existing provider fallback rules in place. Availability and cache behavior vary by provider, so the gateway reports eligibility and usage for each request. Get started today with our documentation and test your existing workloads.
輸出 586 tok (+443 思考) 延遲 7.7 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-0813",
# model="gpt-6-sol", # 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)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: "gpt-6-sol", // 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",
});
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": "gpt-6-sol", # 取消這一行的註解,並把上一行註解掉
"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: "gpt-6-sol", // 取消這一行的註解,並把上一行註解掉
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("gpt-6-sol") // 取消這一行的註解,並把上一行註解掉
.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 (0813) 和 GPT-6 Sol 哪個比較便宜?
以「輸入 / 1M tokens」來看,DeepSeek V4 Pro (0813) 比較便宜($1.32 對 $2,相差 1.5×)。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 (0813) 和 GPT-6 Sol 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 (0813) 與 GPT-6 Sol 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。