Claude Sonnet 5 vs Kimi K3
什么时候选哪个
两者都接受文本和图像输入并返回文本,但 claude-sonnet-5 每百万输入 $2、输出 $10,对比 kimi-k3 的 $3 和 $15——两项都低 1.5 倍——而且它允许关闭思考,kimi-k3 不允许。需要视频输入或超长生成时选 kimi-k3,它 1048576 token 的上下文也可以用在输出上,而 claude-sonnet-5 的上限是 128000 token。其余情况下 claude-sonnet-5 是更便宜的默认选项,缓存读取也是每百万 $0.2 对 $0.3。
Benchmark 成绩
6 项两边都有成绩。
供应商公布: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
价格
| Claude Sonnet 5 | Kimi K3 | Δ | |
|---|---|---|---|
| 输入 / 1M token | $2 | $3 | 0.67× |
| 输出 / 1M token | $10 | $15 | 0.67× |
| 缓存读取 / 1M token | $0.2 | $0.3 | 0.67× |
| 缓存写入 | 1.25x (5m) / 2x (1h) | - | - |
价格取自构建时的实时目录,最新价格见各模型页面。
两个模型所处的位置:全部 76 个按同一单位计费的聊天模型的每 1M token 输入价分布(对数刻度)
能力
| Claude Sonnet 5 | Kimi K3 | |
|---|---|---|
| 工具调用 | 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(由你标记前缀) | 隐式(自动) |
| 缓存有效期 | 5m default, 1h option | 未公布 |
| 最小缓存前缀 | 1024 个 token | 未公布 |
规格
| Claude Sonnet 5 | Kimi K3 | |
|---|---|---|
| 输入模态 | 文本 图像 | 文本 图像 视频 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-06-30 | 2026-07-16 |
| 知识截止日期 | 2026-01 | - |
| 上下文窗口 | 1M | 1M |
| 最大输出 | 128K | 1M |
| 思考参数 |
| reasoning_effort (top-level; the thinking object is not accepted) |
| 可选值 | thinking.type
effort
"enabled" returns 400 | reasoning_effort
|
| 默认值 | thinking on (adaptive) effort
| max |
规格照录自各供应商的文档;供应商没有公布的项目,对应的行直接省略,不做推断。 完整来源: Claude Sonnet 5 · Kimi K3
同一条提示词,两个模型,经网关实测
Claude Sonnet 5 通过 · 3 sentences
Reasoning mode works by having the model generate extended internal "thinking" steps before producing its final answer, and since we're billed on total tokens, that hidden reasoning text adds significantly to what we pay for—even though you never see it in the output. This is different from simply getting longer visible responses; the model is essentially "showing its work" behind the scenes, and complex prompts can trigger thousands of extra reasoning tokens per request. The upside is improved accuracy on complex tasks, but if we want to control costs, we should selectively enable reasoning only for queries that truly need it, rather than applying it universally.
输出 194 tok 延迟 4.3 s
Kimi K3 通过 · 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.
输出 755 tok (+637 思考) 延迟 20.8 s
指令遵循(恰好三句,数得出来)、受众适配(对 CFO 说话的口吻),以及下方 token 计数暴露出的隐藏思考计费差额。
Claude Sonnet 5 通过 · 8/8 cases
## The Bug The function has two related off-by-one issues rooted in the same cause: `cur` and `best` are initialized to `0` instead of `1`, treating run lengths as the number of *matches* between adjacent elements rather than the number of *elements* in the run. This means a single-element input never enters the loop (since `range(1, 1)` is empty) and returns `0` instead of the correct answer of `1`. It also means that for any input, the run length is undercounted by exactly one — a run of 3 equal elements only produces 2 "match" increments, so `best` ends up as 2 instead of 3. The claim that it "misses runs that end at the last index" is actually a symptom of this same undercount: the logic does update `best` correctly on every iteration (including the last), but because it's counting matches instead of elements, the final reported value is always one less than the true longest run. […]
输出 536 tok 延迟 7.1 s
Kimi K3 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 ``` 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. […]
输出 1837 tok (+1547 思考) 延迟 47.2 s
修复是否真的正确(能运行)、解释的信息密度,以及在一个范围明确的任务上的 token 效率。
Claude Sonnet 5 通过 · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11.5, "guidance": null } ```
输出 348 tok 延迟 5.3 s
Kimi K3 通过 · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }
输出 924 tok (+863 思考) 延迟 25.9 s
是否严守 schema(不臆造字段)、能否顶住幻觉压力(原文明说暂不给出 guidance),以及结构化输出路径的差异。
Claude Sonnet 5 通过 · 123 words, 0 banned, 1 question
## Introducing Cross-Provider Prompt Caching We're rolling out a new caching layer for our API gateway that works across every major LLM provider you connect through it. Instead of resending identical prompts and paying full price each time, the gateway recognizes repeated requests and serves cached responses in milliseconds—regardless of whether you're routing to OpenAI, Anthropic, or Google. What does this mean for your bill and your latency? Both drop, often significantly, especially for teams running high-volume, repetitive workloads like customer support bots or batch content generation. The cache is configurable per route, with adjustable TTLs and invalidation rules, so you stay in control of freshness versus cost. Available now for all Pro and Enterprise plans. Check your dashboard to enable it today.
输出 259 tok 延迟 4.8 s
Kimi K3 通过 · 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.
输出 1527 tok (+1354 思考) 延迟 37.9 s
是否守住约束(字数预算、禁用词表、只能有一个问句)、文风特征,以及长度控制。
改一行代码就能在两个模型之间切换
下方每个标签页里都有两个模型 ID,高亮的那两行是唯一要改的地方。端点不变,API key 不变,请求结构也不变。
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="claude-sonnet-5",
# model="kimi-k3", # 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-sonnet-5",
// model: "kimi-k3", // 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-sonnet-5",
# "model": "kimi-k3", # 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-sonnet-5",
// Model: "kimi-k3", // 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-sonnet-5")
// .model("kimi-k3") // 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 Sonnet 5 和 Kimi K3 哪个更便宜?
按「输入 / 1M token」算,Claude Sonnet 5 更便宜($2 对 $3,相差 1.5×)。其他计费项的结论可能相反,完整价格见上方表格,实际成本取决于你的用量构成。
不用分别集成两次,就能对 Claude Sonnet 5 和 Kimi K3 做 A/B 测试吗?
可以。两个模型走同一个 OpenAI 兼容端点,用同一个 API key,切换时只要改一行里的模型名,所以可以给两个模型各分一部分流量,直接对比账单。
Claude Sonnet 5 和 Kimi K3 支持提示词缓存吗?
支持。两个模型的缓存读取价都低于各自的输入价,所以前缀能反复命中缓存的负载,实际成本会比按官网价估算的低。具体的缓存读取价见上方价格表。