GLM-5 對比 GLM-5.2:價格與規格實測

Q: GLM-5 和 GLM-5.2 哪個比較便宜？

GLM-5 在 輸入 / 1m tokens 上較便宜（$1 對比 $1.4，相差 1.4×）。其他項目可能呈現相反結果 — 上表提供完整資訊，實際成本取決於您的使用組合。

何時用哪一個

這兩個 Z.ai 模型在模態（文字進、文字出）、能力標誌（聊天、程式碼、推理、工具、長上下文）、131072 最大輸出 token 和可選思考上完全一致。區別有兩處。上下文：2026-06-16 發布的 glm-5.2 支援 1000000 token，是 2026-02-12 的 glm-5 的 200000 的五倍，並新增了推理力度調節。價目表：glm-5 在兩條 token 線上都低約 1.4 倍，輸入 $1 對 $1.4，輸出 $3.2 對 $4.4，快取讀取低 1.3 倍，$0.2 對 $0.26。整庫或大語料提示選 glm-5.2；任務能裝進 200000 token 且在意價格時留在 glm-5。

Benchmark 成績

領先高於同儕均值無人分數更高GLM-5115 ~~/ 52~~2 ~~/ 52~~GLM-5.21626 ~~/ 70~~1 ~~/ 70~~

雙方都被測過的 17 項。

GLM-5 GLM-5.2 其他被測模型同儕均值 ★ 無人分數更高

SWE-Bench Pro

55.1%

62.1%

Cybergym

43.2%

N/A

GDPval-AA v2 Elo · 642-1861

N/A

1510

Harvey Lab-AA

N/A

91%

GPQA Diamond

86%

91.2%

MCP-Atlas

69.8%

82.6%

廠商公布: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

定價

	GLM-5	GLM-5.2	Δ
輸入 / 1M tokens	$1	$1.4	0.71×
輸出 / 1M tokens	$3.2	$4.4	0.73×
快取讀取 / 1M tokens	$0.2	$0.26	0.77×

費率取自建置時的即時目錄；各模型頁面皆附有目前的費率卡。

它們的相對位置 — 在此計費單位下，所有 64 個聊天模型的每 1M tokens 的輸入價格（對數尺度）

GLM-5 · $1 GLM-5.2 · $1.4

$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

	GLM-5	GLM-5.2
工具使用	是	是
思考控制	可配置	可配置
結構化輸出	是	是
提示快取	隱式（自動）	隱式（自動）
快取生命週期	未公開	未公開
最小快取前綴	未公開	未公開

規格

	GLM-5	GLM-5.2
輸入模態	文字	文字
輸出模態	文字	文字
發布日期	2026-02-12	2026-06-16
上下文視窗	200K	1M
最大輸出	131K	131K
思考參數	thinking.type	thinking.type reasoning_effort
可接受的值	thinking.type enabled disabled	thinking.type enabled disabled reasoning_effort none minimal low medium high xhigh max (none and minimal skip thinking, low and medium map to high, xhigh maps to max)
預設值	enabled, and on GLM-5 the model automatically determines whether to think	enabled, with reasoning_effort at max: the only GLM with an effort dial, and it defaults to the top of it

規格摘錄自各供應商的文件；供應商未發布的資料列會直接省略，而非自行推測。完整來源： GLM-5 · GLM-5.2

單一提示詞，兩款模型 — 經由閘道測量

針對 CFO 的推論修復包含錯誤的函式擷取至 schema 依照限制條件撰寫

提示詞 Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. 檢查恰好 3 句

GLM-5 通過 · 3 sentences

Enabling reasoning forces the model to perform multiple hidden steps to "think" through a problem, drastically increasing the volume of data processed per query compared to a standard response. Because our billing is directly tied to this processing volume, the additional computational work required for higher accuracy has proportionally doubled our consumption. Essentially, the spike reflects a trade-off where we are paying a higher variable cost to secure significantly better analytical outcomes.

輸出 1393 tok (+1308 思考) 延遲 36.0 s

GLM-5.2 通過 · 3 sentences

Enabling reasoning means the LLM now generates thousands of invisible "thinking" tokens to systematically work through complex problems before producing a final answer. Because our cloud providers bill for these internal processing steps at the same rate as standard output, our billable token volume per query has doubled. While this increases our direct API costs, it drastically reduces error rates and manual review labor, ultimately lowering our total cost per resolved transaction.

輸出 1223 tok (+1138 思考) 延遲 17.1 s

指令遵循（恰好三句，可數）、受眾適配（面向 CFO 的語氣），以及下方 token 計量所暴露的隱藏思考計費缺口。

提示詞 This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. 檢查修復通過測試

GLM-5 通過 · 8/8 cases

Here is the fixed code: ```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 `best` and `cur` to zero, which causes the function to count the number of *transitions* between adjacent elements rather than the total number of items in the run, resulting in a return value that is always one less than the actual length (reporting 0 for a single element and 1 for a pair). By initializing the counters to 1 and resetting `cur` to 1 when a streak breaks, the logic correctly counts the items themselves; adding an explicit check for an empty list ensures the function handles the zero-element edge case correctly.

輸出 2907 tok (+2694 思考) 延遲 73.7 s

GLM-5.2 未命中 · 1/8 cases (fails [1])

```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 […]

輸出 4097 tok (+4036 思考) 延遲 58.4 s

修復是否真的正確（可執行）、解釋的資訊密度，以及在一個邊界明確的任務上的 token 效率。

提示詞 Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. 檢查合法 JSON，schema 精確

GLM-5 通過 · 5/5 fields, guidance "withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "withheld pending the Q4 close" } ```

輸出 3620 tok (+3561 思考) 延遲 91.8 s

GLM-5.2 通過 · 5/5 fields, guidance "withheld"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "withheld" } ```

輸出 1947 tok (+1893 思考) 延遲 30.9 s

schema 服從度（不臆造欄位）、幻覺壓力（guidance 明確被暫緩給出），以及結構化輸出路徑的差異。

提示詞 Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. 檢查 120 詞，0 個禁用詞

GLM-5 通過 · 119 words, 0 banned, 1 question

We are thrilled to introduce Global Prompt Caching, a powerful new capability within our API gateway designed to optimize your AI operations. By intelligently storing prompt responses across every supported provider, this feature drastically reduces latency and cuts operational costs. Instead of processing identical requests repeatedly, our system serves cached results instantly, ensuring consistent performance even during high-traffic periods. Why pay full price for repeated inference on the same inputs? This update gives developers fine-grained control over cache lifetimes and hit rates, allowing for predictable budgeting and faster application response times. You can activate this functionality directly in your dashboard settings today. Start maximizing your efficiency now and deliver a snappier experience to your end-users without unnecessary API expenditure.

輸出 715 tok (+571 思考) 延遲 18.9 s

GLM-5.2 通過 · 120 words, 0 banned, 1 question

We are introducing Caching for our API Gateway, the smartest way to optimize your workflows. Why pay for the exact same response twice? Now, you can automatically store and reuse prompt results across multiple AI providers, drastically reducing latency and overall operational costs. If a user submits a duplicate query, the gateway serves the cached answer instantly, regardless of whether you route to OpenAI, Anthropic, or others. This directly translates to faster applications and significantly lower monthly API bills. You can easily configure your specific caching rules within the developer dashboard and watch your efficiency soar. Stop wasting your valuable tokens on completely redundant computations. Upgrade to the latest gateway version today and experience the future of intelligent prompt management.

輸出 11125 tok (+10984 思考) 延遲 114.8 s

約束服從度（字數預算、禁用詞表、唯一的那句問句）、文風指紋，以及長度控制。

只需一行程式碼即可在兩者間切換

以下每個頁籤中都有這兩個 ID — 醒目提示的這兩行是唯一的修改處。相同的端點，相同的金鑰，相同的請求結構。

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="glm-5",
    # model="glm-5.2",  # 取消註解此行，並註解上一行
    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: "glm-5",
  // model: "glm-5.2",  // 取消註解此行，並註解上一行
  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": "glm-5",
    # "model": "glm-5.2",  # 取消註解此行，並註解上一行
    "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: "glm-5",
		// Model: "glm-5.2",  // 取消註解此行，並註解上一行
		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("glm-5")
        // .model("glm-5.2")  // 取消註解此行，並註解上一行
        .addUserMessage("Summarize this diff")
        .reasoningEffort(ReasoningEffort.MEDIUM)
        .build());
System.out.println(resp.choices().get(0).message().content().orElse(""));

取得 API 金鑰 →

常見問題

GLM-5 和 GLM-5.2 哪個比較便宜？

GLM-5 在輸入 / 1m tokens 上較便宜（$1 對比 $1.4，相差 1.4×）。其他項目可能呈現相反結果 — 上表提供完整資訊，實際成本取決於您的使用組合。

我可以在不進行兩次整合的情況下，對 GLM-5 和 GLM-5.2 進行 A/B 測試嗎？

可以。兩者皆透過同一個相容 OpenAI 的端點提供服務，並使用同一把 API 金鑰 — 切換只需更改一行的模型字串，因此您可以將部分流量分別導向兩者並直接比較帳單。

GLM-5 與 GLM-5.2 支援提示快取嗎？

是的 — 兩者的快取讀取費率皆低於其輸入費率，因此具有暖前綴的工作負載成本會低於牌價所示。確切的快取讀取列請見上方的定價表。

GLM-5 vs GLM-5.2

Benchmark 成績

定價

能力

規格

單一提示詞，兩款模型 — 經由閘道測量

只需一行程式碼即可在兩者間切換

常見問題

相關比較