DeepSeek V4 Pro vs Qwen3.8 Max
何时使用哪一个 — 经过整理的结论,而非基准测试表格
大批量纯文本工作选 deepseek-v4-pro:每百万 token 输入更便宜($1.608 对 $2)、输出更便宜($3.216 对 $6,即 Qwen 约 1.87 倍),缓存读取 $0.0134 对 $0.25,并且允许最多 393216 输出 token 而非 131072——思考还可以关闭。需要图像输入时选 qwen3.8-max,它接受文本和图像,而 deepseek-v4-pro 是文本进、文本出。上下文基本持平,1000000 对 983616 token,两者都覆盖对话、代码、推理和工具。
定价
| DeepSeek V4 Pro | Qwen3.8 Max | Δ | |
|---|---|---|---|
| 输入 / 1M tokens | $1.608 | $2 | 0.8× |
| 输出 / 1M tokens | $3.216 | $6 | 0.54× |
| 缓存读取 / 1M tokens | $0.0134 | $0.25 | 0.054× |
| 缓存写入 | 不单独收费 | 1.25x | — |
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 | Qwen3.8 Max | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 可配置 | 是 —— 厂商未公布调节参数 |
| 结构化输出 | 是 | 是 |
| 提示词缓存 | 隐式(自动) | 隐式 + 显式 |
| 缓存生存时间 | no fixed TTL (evicted when unused) | explicit: 5m, reset on hit |
| 最小缓存前缀 | 未公开 | 1024 个 token |
规格
| DeepSeek V4 Pro | Qwen3.8 Max | |
|---|---|---|
| 输入模态 | 文本 | 文本 图像 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-04-24 | 2026-08-03 |
| 上下文窗口 | 1M | 984K |
| 最大输出 | 393K | 131K |
| 思考参数 |
| — |
| 允许的值 | thinking.type
reasoning_effort
| — |
| 默认值 | enabled, with reasoning_effort high some complex agent requests are automatically set to max | — |
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 · Qwen3.8 Max
单个 Prompt,两个模型 —— 通过网关实测
DeepSeek V4 Pro 通过 · 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.
输出 641 tok (+545 思考) 延迟 11.5 s
Qwen3.8 Max 通过 · 3 sentences
Enabling reasoning makes the model produce additional hidden steps before responding, and those tokens are billable. It also tends to lengthen each interaction because the model works through more possibilities before settling on an answer. Therefore, the bill doubled mainly due to higher compute and token usage per request, not necessarily because the number of requests doubled.
输出 378 tok (+305 思考) 延迟 8.6 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。
DeepSeek V4 Pro 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 ``` **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. […]
输出 2418 tok (+2131 思考) 延迟 35.6 s
Qwen3.8 Max 通过 · 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 bug is that the original code starts `best` and `cur` at `0`, so it counts adjacent equal *transitions* rather than the number of items in the run. A run of length `n` has only `n - 1` equal-neighbor transitions, so single-element inputs return `0`, and runs that reach the end are undercounted by one. Initializing the current run to `1` for the first element, resetting it to `1` on a break, and updating `best` from that count fixes the off-by-one.
输出 1616 tok (+1411 思考) 延迟 34.7 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。
DeepSeek V4 Pro 通过 · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": "eleven and change", "guidance": null }
输出 1204 tok (+1153 思考) 延迟 19.9 s
Qwen3.8 Max 通过 · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }
输出 1199 tok (+1141 思考) 延迟 24.4 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。
DeepSeek V4 Pro 没有可供评分的回答 · no answer text within 16,384 tokens (all of it went to thinking)
模型未返回回答文本 —— 整个 token 预算都用在了隐藏思考上。
输出 8193 tok (+8192 思考) 延迟 106.2 s
Qwen3.8 Max 通过 · 120 words, 0 banned, 1 question
Today, our API gateway adds prompt caching across major model providers. It stores prompts and responses in one fast cache layer. Teams can lower token spend, reduce latency, and repeat reliable answers. The feature supports OpenAI, Anthropic, Google, and Mistral through one configuration. You can set retention rules, scope access, and invalidate entries quickly. How does your team maintain consistent results during provider outages? Approved cached responses keep applications stable while fallback routes recover. The dashboard shows hit rates, savings, latency, and provider usage. Engineers receive audit trails for every cached prompt, enabling safer testing. Product managers can compare cost trends before and after cache adoption. Start with a small route, then safely expand caching to production traffic right now.
输出 2744 tok (+2591 思考) 延迟 46.3 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",
# model="qwen3.8-max", # 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)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: "qwen3.8-max", // 取消注释此行,注释上一行
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": "qwen3.8-max", # 取消注释此行,注释上一行
"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: "qwen3.8-max", // 取消注释此行,注释上一行
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("qwen3.8-max") // 取消注释此行,注释上一行
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));常见问题
DeepSeek V4 Pro 和 Qwen3.8 Max 哪个更便宜?
在 输入 / 1m tokens 方面,DeepSeek V4 Pro 更便宜($1.608 对比 $2,相差 1.2×)。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 和 Qwen3.8 Max 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 和 Qwen3.8 Max 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。