Coding and agentic model with a 1M token context, 128K output, always-on reasoning at low, high, or max effort, native web search, and tool calling.
Z.ai文本生成1M 上下文发布日期 2026年8月14日Singapore专有端点新Coding and agentic model with a 1M token context, 128K output, always-on reasoning at low, high, or max effort, native web search, and tool calling.
Notes: - Context window: 1M tokens - Maximum output: 128K tokens - Always reasons; thinking cannot be disabled - Reasoning effort: low, high, or max (max recommended for complex coding) - A request for a different effort, or to turn thinking off, is served at the nearest supported level - Built-in web search adds $0.033 per request when used - Supports function calling, structured output (JSON mode), and streaming
也称为 Z.ai GLM 5.3
glm-5-3/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/glm-5-3:generateContentglm-5.3zai/glm-5.3zhipu/glm-5.3来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费，没有月度最低消费。
GLM 5.3 提供 OpenAI 兼容的 Chat Completions API。用你的 EmpirioLabs API 密钥把任意 OpenAI SDK 指向 https://api.empiriolabs.ai/v1，并使用模型 ID glm-5-3。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5-3",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="glm-5-3",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)EmpirioLabs 上 GLM 5.3 API 支持的请求参数。省略字段时使用默认值。
| 参数 | 类型 | 默认值 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| max_tokens | integer | 65536 | 1 到 131072 | Maximum number of output tokens to generate. |
| temperature | number | 1 | 0 到 1 | Controls randomness. Lower values make responses more deterministic. |
| top_p | number | 0.95 | 0.01 到 1 | Nucleus sampling cutoff. |
| reasoning_effort | enum | max | low, high, max | GLM 5.3 reasoning effort. This model always reasons and cannot be turned off. low is lightweight, high is enhanced, and max is deep reasoning. max is recommended for... |
| do_sample | boolean | true | - | Enable sampling. Turn off for greedy deterministic output (temperature and top_p are ignored). |
| tool_web_search | boolean | false | - | Enable built-in web search. Adds $0.033 per request when used. |
| search_recency_filter | enum | noLimit | oneDay, oneWeek, oneMonth, oneYear, noLimit | Limit web search results to a recency window. |
| count | integer | 10 | 1 到 50 | Number of web search results to retrieve when web search is enabled. |
| search_domain_filter | string | - | - | Restrict web search to a specific domain. |
| search_prompt | string | - | - | Optional prompt used to summarize retrieved web search results. |
| search_result | boolean | true | - | Return web search result metadata in the response when web search is enabled. |
| tool_stream | boolean | false | - | Stream function-call arguments incrementally when streaming. |
| tools | array | [] | - | OpenAI-compatible function calling tool definitions. |
| tool_choice | object | - | - | OpenAI-compatible tool choice control. |
在 EmpirioLabs，GLM 5.3 按量计费：Input $1.40 per 1M prompt tokens; Output $4.40 per 1M generated tokens; Web search $0.033 per request。本页的实时价格表始终与 API 的实际计费一致。
GLM 5.3 支持 1M token 的上下文窗口，每次响应最多 131,072 个输出 token。
兼容。GLM 5.3 提供 OpenAI 兼容的 Chat Completions API，现有 OpenAI SDK 只需把 base_url 指向 https://api.empiriolabs.ai/v1 并把模型 ID 设为 glm-5-3 即可使用。
可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 GLM 5.3，你可以在写代码之前先测试提示词。
创建 EmpirioLabs 账户，然后在控制台的 API Keys生成密钥。计费使用按量付费的额度，只为实际发出的请求付费。
