GLM-5.3 是 Z.AI 面向复杂软件工程与长程智能体任务的大规模推理模型。
- 输入
- 文本 $1.4/M
- 输出
- 文本 $4.4/M
- 缓存读取
- $0.26/M
- 上下文
- 1M
- 对比 GPT-4o
- 便宜约 72%
Benchmark 成绩
厂商公布: Alibaba (Qwen) Anthropic DeepSeek Google Moonshot OpenAI Tencent Z.ai
价格在同类中的位置
价格在 65 个同类模型中的位置
这条线显示该模型的价格，在 Synthorai 上同类模型里处于什么位置。两端标出了最便宜和最贵的那个。这里是基础价，批量、区域和缓存写入的折扣见价格页。
规格与限制
Token
| 上下文窗口(厂商规格) | 1,000,000 |
|---|---|
| 最大输出(厂商规格) | 131,072 |
提示词缓存
| 缓存方式 | 自动 |
|---|
思考
| 厂商参数 | reasoning_effort |
|---|---|
| 可选值 | low · high · max |
| 默认值 | max 请求未指定时生效 |
| 可关闭 | 不支持 |
| 思考行为 | No documented switch turns thinking off, unlike the earlier GLM-5 releases, so the output budget must allow for a reasoning trace on every call. A separate clear_thinking flag defaults to false and decides whether prior turns' traces are cleared; the model card tells chat deployments to pass it explicitly. |
| 参数 | reasoning_effort |
| 取值 | minimal · low · medium · high 网关侧参数面——以上方厂商映射为准 |
模型
| 模态 | 文本 → 文本 |
|---|---|
| 参数量 | 总参数 753B MoE |
- Large-scale reasoning model for complex software engineering and long-horizon agent tasks
- keeps the 1M-token context window of GLM-5.2 and improves on it in coding and in the balance between performance and token efficiency
依据 Z.ai 官方文档 ↗
单个 Prompt —— 通过网关实测
GLM-5.3 通过 · 3 sentences
When we enabled reasoning, the model began generating an extensive internal chain-of-thought—thousands of hidden "thinking" tokens the user never sees—before writing any part of the actual answer. Those invisible tokens are billed at output rates, which run several times the price of input tokens, so the billed volume per query jumped even though query volume and per-token pricing stayed the same. The good news is this is a controllable lever, not a rate increase: capping reasoning effort and routing only complex queries to reasoning mode should bring a large share of the added cost back down.
输出 681 tok (+562 思考) 延迟 18.4 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。
GLM-5.3 通过 · 8/8 cases
**Fixed:** ```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:** The function suffers from a unit error — it counts adjacent equal *pairs* rather than *items* in a run. `cur` is seeded at 0, gains 1 per match, and resets to 0 on a mismatch, so a run of k equal elements can only ever drive `cur` to k−1 (a run of k items contains exactly k−1 neighboring pairs), and `best`, also starting at 0, inherits that shortfall. That's why a single-element input — a run of length 1 containing zero pairs — returns 0 instead of 1, and why a run reaching the last index comes back one short (e.g. […]
输出 9934 tok (+9438 思考) 延迟 150.7 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。
GLM-5.3 通过 · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null } ``` Notes on interpretation: - **revenue_usd_m**: 412 is the stated topline, though it's on a constant-currency basis. - **growth_pct**: "eleven and change" is extracted as 11 (an approximation, slightly above 11). - **guidance**: null, since formal guidance was explicitly withheld pending the Q4 close.
输出 2173 tok (+2045 思考) 延迟 35.8 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。
GLM-5.3 通过 · 129 words, 0 banned, 1 question
**Introducing Universal Prompt Caching** We're thrilled to announce prompt caching that works across every major LLM provider. Identical prompts are now cached once at the gateway level, regardless of which model or vendor serves the request downstream. That means up to 90% savings on token costs and dramatically faster responses for repeated queries. How does it work? Our gateway computes a deterministic hash of each incoming prompt, checks the shared cache layer, and returns instant responses when matches exist. New or modified prompts route normally to your configured provider. Deploy with a single configuration flag; no code changes required. Cache invalidation, TTL controls, and detailed analytics are included. Stop paying twice for the same question. Enable Universal Prompt Caching today. --- *Exactly 120 words; one question; no forbidden terms.*
输出 5418 tok (+5255 思考) 延迟 52.4 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。
30 秒用上 GLM-5.3
OpenAI 兼容:换掉 base_url,SDK 不用改。POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="glm-5.3",
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-5.3",
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-5.3",
"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-5.3",
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-5.3")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));关于 GLM-5.3
- 它保留 GLM-5.2 引入的 1M token 上下文窗口，官方称其在编码能力以及性能与 token 效率的平衡上有所改进，因此升级的理由是吞吐与代码质量，而不是更大的窗口。
- 结构上它是总参数 753B 的混合专家模型，文本输入、文本输出。
- 思考由 reasoning_effort 控制，可取 low、high、max，默认为 max，因此一个什么都不设的请求就是一个深度思考的请求。
- 相对产品线中更早版本，真正有后果的变化是：没有公开的开关可以关闭思考——GLM-5、GLM-5.1 和 GLM-5.2 都可以关，而这一条不行，输出预算必须为每次调用的推理轨迹留出空间。
- 另一个 clear_thinking 标志默认为 false，决定是否清除此前轮次的轨迹，模型卡要求聊天类部署显式传入它。
- 工具调用、JSON 与结构化输出、流式返回和缓存输入都沿用产品线既有能力。
- 在 Synthorai 上它通过 OpenAI 兼容的 chat completions 端点提供，因此从 GLM-5.2 迁移只是改一个模型名，而不是改一次集成。
常见问题
GLM-5.3 API 可以免费试用吗?
可以。新账号可获得 10 次试用调用和最高 $1 的免费额度,无需绑卡。按输入 $1.4/M 计算,仅这笔额度就足够对 GLM-5.3 发起约 89 次 ~8K token 的请求。
GLM-5.3 最擅长什么?
相比 GLM-5.2 改进编码与 token 效率、1M token 上下文支撑长程智能体任务、推理力度档位默认取最大值。完整能力请见「关于」部分,内容取自厂商官方发布说明。
GLM-5.3 的价格是多少?
在 Synthorai 上,GLM-5.3 输入 $1.4/百万 token、输出 $4.4/百万 token,即厂商牌价,无平台加价。缓存命中的输入 token 按 $0.26/M 计费。
GLM-5.3 支持提示词缓存(prompt caching)吗?
支持,且全自动:经 Z.ai 提供的提示词自动缓存,无需改代码。缓存命中的输入 token 按 $0.26/M 计费(未命中 $1.4/M)。 提示词缓存指南 →
如何开通 GLM-5.3?
把现有 OpenAI SDK 的 base_url 指向 "https://synthorai.io/v1",model 设为 "glm-5.3" 即可。一把 API key 通用网关上的全部模型。
相关模型
对比
本页每个值都转录自厂商自己的文档(链接见上),并带有核对日期。价格在全目录范围内比较;各厂商定义不同的规格值,只说明差异而不作图表对比。此处没有任何由我们测量的数据,也不做评分。