GLM-5 vs Qwen3.7 Plus
什么时候选哪个
qwen3.7-plus 是更便宜、更宽的默认选择：输入 $0.4、输出 $1.6 对 glm-5 的 $1 和 $3.2，输入便宜 2.5 倍、输出便宜 2 倍，缓存读取 $0.08 对 $0.2，上下文 1000000 token 对 200000，还接受图像和视频加文本。两者都有聊天、代码、推理、工具和长上下文标志，都可关闭思考。需要单次回复超过 65536 token（glm-5 最多允许 131072），或已锁定在 GLM 家族时选 glm-5。
Benchmark 成绩
9 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
| GLM-5 | Qwen3.7 Plus | Δ | |
|---|---|---|---|
| 输入 / 1M token | $1 | $0.4 | 2.5× |
| 输出 / 1M token | $3.2 | $1.6 | 2× |
| 缓存读取 / 1M token | $0.2 | $0.08 | 2.5× |
| 缓存写入 | - | 1.25x | - |
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 78 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
| GLM-5 | Qwen3.7 Plus | |
|---|---|---|
| 工具调用 | 是 | 是 |
| 思考控制 | 可配置 | 可配置 |
| 结构化输出 | 是 | 是 |
| 提示词缓存 | 隐式（自动） | 隐式 + 显式 |
| 缓存有效期 | 未公布 | explicit: 5m, reset on hit |
| 最小缓存前缀 | 未公布 | 1024 个 token |
规格
| GLM-5 | Qwen3.7 Plus | |
|---|---|---|
| 输入模态 | 文本 | 文本 图像 视频 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-02-12 | 2026-06-01 |
| 上下文窗口 | 200K | 1M |
| 最大输出 | 131K | 66K |
| 思考参数 | thinking.type |
|
| 可选值 | thinking.type
| enable_thinking
thinking_budget
preserve_thinking
|
| 默认值 | enabled, and on GLM-5 the model automatically determines whether to think | on the Qwen3.7 Plus series is hybrid thinking with thinking enabled by default, and preserve_thinking is off |
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： GLM-5 · Qwen3.7 Plus
同一条提示词，两个模型，经网关实测
GLM-5 通过 · 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.
输出 1393 tok (+1308 思考) 延迟 36.0 s
Qwen3.7 Plus 通过 · 3 sentences
Enabling reasoning requires the model to generate extensive internal "thinking" tokens to process complex logic before delivering a final answer. Because our vendor charges us per token consumed, this hidden computational overhead effectively doubles our output volume for the exact same number of user requests. Consequently, our costs have doubled because we are now paying for the model's increased processing time to achieve higher-quality, more accurate results.
输出 1428 tok (+1345 思考) 延迟 25.2 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。
GLM-5 通过 · 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.
输出 2907 tok (+2694 思考) 延迟 73.7 s
Qwen3.7 Plus 通过 · 8/8 cases
## 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 else: cur = 1 best = max(best, cur) return best ``` ## Bug Explanation The function has two related bugs rooted in how it counts run lengths. First, `cur` is initialized to `0` and only incremented on matches, so it counts the number of *transitions* between equal elements rather than the total elements in the run—a run of N identical items only reaches `cur = N − 1`, undercounting by one. This also causes the single-element case to return `0`, since the loop never executes and `cur` never increments. […]
输出 2317 tok (+2005 思考) 延迟 40.5 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。
GLM-5 通过 · 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" } ```
输出 3620 tok (+3561 思考) 延迟 91.8 s
Qwen3.7 Plus 通过 · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }
输出 1807 tok (+1750 思考) 延迟 31.6 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。
GLM-5 通过 · 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.
输出 715 tok (+571 思考) 延迟 18.9 s
Qwen3.7 Plus 通过 · 120 words, 0 banned, 1 question
Introducing PromptCache, our new API gateway feature designed to store and reuse prompts across multiple artificial intelligence providers. Have you ever noticed how repeatedly sending identical queries drains your budget and increases latency? PromptCache solves this by intelligently storing responses at the gateway level. When your application requests the same prompt from a different provider, the system instantly returns the cached result. This drastically reduces API costs and accelerates response times for your users. You can configure custom expiration times and set specific fallback rules for each vendor. You must stop paying twice for the exact same computation. Please upgrade your entire infrastructure today and experience much faster and cheaper integrations without changing a single line of your application code.
输出 4453 tok (+4312 思考) 延迟 76.8 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="glm-5",
# model="qwen3.7-plus", # 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: "glm-5",
// model: "qwen3.7-plus", // 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": "glm-5",
# "model": "qwen3.7-plus", # 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: "glm-5",
// Model: "qwen3.7-plus", // 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("glm-5")
// .model("qwen3.7-plus") // 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
GLM-5 和 Qwen3.7 Plus 哪个更便宜？
按「输入 / 1M token」算，Qwen3.7 Plus 更便宜（$0.4 对 $1，相差 2.5×）。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 GLM-5 和 Qwen3.7 Plus 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。
GLM-5 和 Qwen3.7 Plus 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。