Claude Opus 5 vs DeepSeek V4 Pro (0813)
何时使用哪一个 — 经过整理的结论,而非基准测试表格
两者均具有 1,000,000 token 的上下文窗口并涵盖对话、代码、工具和推理,因此区别主要在于输入、输出长度和价格:claude-opus-5 还接受图像输入并允许你关闭 thinking,而 deepseek-v4-pro-0813 仅支持文本,但允许高达 393,216 的输出 token,而前者为 128,000。在价格表上,deepseek-v4-pro-0813 的输入价格约便宜 3.8 倍($1.32 对比 $5),输出价格约便宜 6.3 倍($3.96 对比 $25),缓存读取价格为 $0.132 对比 $0.5。如果需要图像输入或可控的 thinking,请选择 Anthropic 的模型;如果需要以更低成本生成长文本,请选择 DeepSeek 的模型。
定价
| Claude Opus 5 | DeepSeek V4 Pro (0813) | Δ | |
|---|---|---|---|
| 输入 / 1M tokens | $5 | $1.32 | 3.8× |
| 输出 / 1M tokens | $25 | $3.96 | 6.3× |
| 缓存读取 / 1M tokens | $0.5 | $0.132 | 3.8× |
| 缓存写入 | 1.25x (5m) / 2x (1h) | 不单独收费 | — |
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
| Claude Opus 5 | DeepSeek V4 Pro (0813) | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 可配置 | 始终开启 |
| 结构化输出 | 是 | 是 |
| 提示词缓存 | 显式(由您标记前缀) | 隐式(自动) |
| 缓存生存时间 | 5m default, 1h option | no fixed TTL (evicted when unused) |
| 最小缓存前缀 | 1024 个 token | 未公开 |
规格
| Claude Opus 5 | DeepSeek V4 Pro (0813) | |
|---|---|---|
| 输入模态 | 文本 图像 | 文本 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-07-24 | 2026-08-13 |
| 知识截止日期 | 2026-05 | — |
| 上下文窗口 | 1M | 1M |
| 最大输出 | 128K | 393K |
| 思考参数 |
| reasoning_effort |
| 允许的值 | thinking.type
effort
| reasoning_effort
|
| 默认值 | thinking on effort
| — |
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: Claude Opus 5 · DeepSeek V4 Pro (0813)
单个 Prompt,两个模型 —— 通过网关实测
Claude Opus 5 通过 · 3 sentences
When reasoning is enabled, the model generates a hidden chain of "thinking" tokens before it writes the visible answer, and those internal tokens are billed at the output rate even though no one ever sees them — commonly 3–10x more tokens than the response itself. Because output tokens are priced several times higher than input tokens, that added volume hits us at our most expensive rate, which is why the bill roughly doubled while our request count stayed flat. The spend is controllable: we can cap the reasoning budget per call, route only genuinely hard requests to reasoning mode and cheaper models for the rest, and track cost per successfully completed task rather than cost per token, since a single correct answer usually beats three cheap retries plus human cleanup.
输出 529 tok 延迟 9.0 s
DeepSeek V4 Pro (0813) 通过 · 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.
输出 308 tok (+226 思考) 延迟 5.1 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。
Claude Opus 5 通过 · 8/8 cases
## Fixed version ```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 if cur > best: best = cur return best ``` ## The bug The counters were tracking the wrong quantity: `cur` counted *matching adjacent pairs* rather than *elements in the current run*, and both counters started at `0` instead of `1`. Since a run of length *n* contains only *n − 1* adjacent equal pairs, every result came back one too small — `[1, 1]` returned 1, `[3, 3, 3]` returned 2 — and a single-element list returned 0 because the loop body never executed and `best` kept its initial value of `0`. […]
输出 1094 tok 延迟 16.1 s
DeepSeek V4 Pro (0813) 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 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.
输出 1315 tok (+1130 思考) 延迟 16.9 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。
Claude Opus 5 通过 · 5/5 fields, guidance "Withheld pending Q4 close"
```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending Q4 close" } ``` Notes on judgment calls: - **quarter**: "September quarter" is labeled Q3 because the text refers to an upcoming "Q4 close," implying a calendar-aligned fiscal year. No fiscal year is given. - **revenue_usd_m**: 412 is stated as constant-currency and hedged ("call it"), so it's approximate; the currency is not explicitly stated as USD. - **growth_pct**: "up eleven and change" means slightly more than 11, so 11 is a floor rather than an exact figure.
输出 539 tok 延迟 7.6 s
DeepSeek V4 Pro (0813) 通过 · 5/5 fields, guidance null
{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11.0,"guidance":null}
输出 2155 tok (+2121 思考) 延迟 26.0 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。
Claude Opus 5 通过 · 123 words, 0 banned, 1 question
**Cross-Provider Prompt Caching** We're introducing Cross-Provider Prompt Caching in the API Gateway. Repeated system prompts, long documents, and few-shot examples are stored once at the gateway layer and reused across OpenAI, Anthropic, Google, and self-hosted models. Instead of paying full input token costs on every request, your application sends a cache reference, and the gateway rehydrates the context before forwarding it downstream. Why does that matter? Teams running high-volume agents and retrieval pipelines typically see input token spend fall 40 to 70 percent, with median latency dropping by several hundred milliseconds. Caches are scoped per project, encrypted at rest, and invalidated automatically when a prompt template changes. Enable it with a single header, and see the docs for TTL tuning and per-route controls.
输出 1593 tok 延迟 19.1 s
DeepSeek V4 Pro (0813) 通过 · 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.
输出 2845 tok (+2694 思考) 延迟 25.5 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="claude-opus-5",
# model="deepseek-v4-pro-0813", # 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: "claude-opus-5",
// model: "deepseek-v4-pro-0813", // 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": "claude-opus-5",
# "model": "deepseek-v4-pro-0813", # 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: "claude-opus-5",
// Model: "deepseek-v4-pro-0813", // 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("claude-opus-5")
// .model("deepseek-v4-pro-0813") // 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
Claude Opus 5 和 DeepSeek V4 Pro (0813) 哪个更便宜?
在 输入 / 1m tokens 方面,DeepSeek V4 Pro (0813) 更便宜($1.32 对比 $5,相差 3.8×)。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 Claude Opus 5 和 DeepSeek V4 Pro (0813) 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。
Claude Opus 5 和 DeepSeek V4 Pro (0813) 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。