Claude Haiku 5.5 vs Kimi K3.1 Pro
什麼情況選哪一個
提示詞不超過 100000 個輸入 token 時,每百萬輸出 token 為 $0.5 和 $10(claude-haiku-5-5 對 kimi-k3.1-pro)。 使用 claude-haiku-5-5 時留意輸入級距:超過 100000 token 後,整筆請求按高檔計費。 與 claude-haiku-5-5 相比,長程程式設計任務需要讀取截圖並回傳結構化結果時,可評估 kimi-k3.1-pro。
定價
| Claude Haiku 5.5 | Kimi K3.1 Pro | Δ | |
|---|---|---|---|
| 輸入 / 1M tokens | $0.1 | $2 | 0.05× |
| 輸出 / 1M tokens | $0.5 | $10 | 0.05× |
| 快取讀取 / 1M tokens | $0.01 | $0.2 | 0.05× |
| 快取寫入 | 1.25x (5m) / 2x (1h) | - | - |
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。 主表顯示基礎級距。提示詞長度可能改變整筆請求的費率,各模型頁有完整價目。
Claude Haiku 5.5 · 依輸入長度分級的價格
整次請求依輸入長度所在級距計費。價格單位為美元/百萬 token。
| 輸入 token 數 | 輸入 | 輸出 | 思考模式輸入 |
|---|---|---|---|
| 0 - 100,000 | $0.1 | $0.5 | - |
| 100,001 - 1,000,000 | $0.5 | $2.5 | - |
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 86 個聊天模型(對數尺度)
功能
| Claude Haiku 5.5 | Kimi K3.1 Pro | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 可設定 | 是,但供應商未公布調整參數 |
| 結構化輸出 | 是 | 是 |
| 提示詞快取 | 顯式(由你標記前綴) | 隱式(自動) |
| 快取存活時間 | 5m default, 1h option | 未公布 |
| 最小快取前綴 | 512 個 token | 未公布 |
規格
| Claude Haiku 5.5 | Kimi K3.1 Pro | |
|---|---|---|
| 輸入模態 | 文字 圖像 | 文字 圖像 |
| 輸出模態 | 文字 | 文字 |
| 發布日期 | 2026-10-07 | 2026-10-23 |
| 知識截止日期 | 2026-06 | - |
| 上下文視窗 | 1,000,000 | 1,048,576 |
| 最大輸出 | 128,000 | 1,048,576 |
| 思考參數 | output_config.effort | - |
| 可接受的值 | output_config.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: Claude Haiku 5.5 · Kimi K3.1 Pro
同一段提示詞,兩個模型,經閘道實測
Claude Haiku 5.5 通過 · 3 sentences
Enabling reasoning makes the model generate a long internal chain of thought before its answer, and those thinking tokens are billed as output tokens, which cost several times more than input tokens. The model often produces many times more output per request than it did without reasoning, so the per-call cost rises even when the visible answer looks about the same length. Because that extra spend scales with every request, the bill roughly doubled, and we can control it by setting reasoning budgets, using reasoning only for tasks that need it, or routing simpler requests to a non-reasoning model.
輸出 332 tok (+159 思考) 延遲 2.9 s
Kimi K3.1 Pro 通過 · 3 sentences
Enabling reasoning makes the model generate extra internal “thinking” tokens before responding, and these are typically billed at output-token rates even though users never see them. If request volume and pricing stayed flat but reasoning substantially increased tokens per request, the total bill could double. Compare pre- and post-change usage reports for reasoning tokens, then control costs with lower reasoning effort, token budgets, cheaper models, and selective use on tasks where the quality gain justifies the spend.
輸出 471 tok (+366 思考) 延遲 14.3 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。
Claude Haiku 5.5 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 bug is that `cur` counts adjacent equal *pairs*, not run *elements*. A run of k equal items produces k−1 matching pairs, so the function returns one less than the true length, and a single-element input produces no pairs at all, so it returns 0 instead of 1. Resetting `cur` to 0 on a mismatch compounds this by starting every run one step behind. The fix starts both `cur` and `best` at 1 (a non-empty list always has a run of at least one element), resets `cur` to 1 on a mismatch, and updates `best` after every element rather than only inside the equal-branch. The empty-list guard keeps the function from returning 1 for `[]`. […]
輸出 1012 tok (+591 思考) 延遲 6.0 s
Kimi K3.1 Pro 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: best = max(best, cur) cur = 1 return max(best, cur) ``` The original `cur` counts matching adjacent pairs rather than items: it starts at 0, so a singleton returns 0, and a run of `k` equal items is recorded as only `k - 1`. Its bookkeeping also never correctly finalizes the current run’s length at end of input. The fix starts every run at 1, records its length when a mismatch ends it, and takes a final `max` after the loop so a run ending at the last index is included; empty input returns 0.
輸出 2984 tok (+2785 思考) 延遲 70.1 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。
Claude Haiku 5.5 通過 · 5/5 fields, guidance "Formal guidance withheld pending the Q4 "
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": 11, "guidance": "Formal guidance withheld pending the Q4 close" } ``` Notes: The text gives revenue as 412 but doesn't state the currency, so I left `revenue_usd_m` as null. Growth is "eleven and change," so 11 is an approximation.
輸出 725 tok (+572 思考) 延遲 4.6 s
Kimi K3.1 Pro 通過 · 5/5 fields, guidance null
{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11,"guidance":null}
輸出 454 tok (+410 思考) 延遲 12.0 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。
Claude Haiku 5.5 通過 · 120 words, 0 banned, 1 question
**Introducing Prompt Cache Sync, the newest feature in GatewayOne.** Teams routing requests across OpenAI, Anthropic, and Google have often paid to process the same long system prompts again and again. Now the gateway stores those prompts once and reuses them wherever they appear, regardless of provider. Repeated context is matched by content hash, so cached prefixes return faster and cost less, with no changes to your application code. How much could this save your team? Enable Prompt Cache Sync from the dashboard, and your next billing report will show the difference. Cache entries follow your existing retention settings and can be purged per project at any time. Availability begins this week for all Scale and Enterprise plans worldwide. Start today.
輸出 2164 tok (+1929 思考) 延遲 9.9 s
Kimi K3.1 Pro 通過 · 120 words, 0 banned, 1 question
Meet Prompt Cache, our new API gateway feature for caching prompts and responses across model providers. It cuts token spend, lowers latency, and keeps applications responsive during traffic surges. Define cache keys, expiration rules, and tenant boundaries in one policy, then apply them to OpenAI, Anthropic, Gemini, or custom models without changing application code. Encryption, redaction, and immediate purges help protect sensitive data, while metrics reveal hit rates, savings, and performance by endpoint and provider. Need a faster way to handle repeated requests? Serve eligible results from cache and preserve your existing routing, fallback, and retry behavior. Available today in beta, Prompt Cache gives platform teams controls for cost, speed, and reliability, with no extra infrastructure to deploy or maintain.
輸出 2740 tok (+2576 思考) 延遲 55.8 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="claude-haiku-5-5",
# model="kimi-k3.1-pro", # 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: "claude-haiku-5-5",
// model: "kimi-k3.1-pro", // 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": "claude-haiku-5-5",
# "model": "kimi-k3.1-pro", # 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: "claude-haiku-5-5",
// Model: "kimi-k3.1-pro", // 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("claude-haiku-5-5")
// .model("kimi-k3.1-pro") // 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
Claude Haiku 5.5 和 Kimi K3.1 Pro 哪個比較便宜?
主表顯示基礎級距。提示詞長度可能改變整筆請求的費率,各模型頁有完整價目。
可以只串接一次,就對 Claude Haiku 5.5 和 Kimi K3.1 Pro 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。
Claude Haiku 5.5 與 Kimi K3.1 Pro 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。