
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.
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
Also known as 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-5.3Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.
GLM 5.3 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id glm-5-3. Get an API key from the EmpirioLabs dashboard.
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)Request parameters supported by the GLM 5.3 API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| max_tokens | integer | 65536 | 1 to 131072 | Maximum number of output tokens to generate. |
| temperature | number | 1 | 0 to 1 | Controls randomness. Lower values make responses more deterministic. |
| top_p | number | 0.95 | 0.01 to 1 | Nucleus sampling cutoff. |
| reasoning_effort | enum | max | low, high, max | This model always reasons and cannot be turned off. low is lightweight, high is enhanced, and max is deep reasoning. max is recommended for complex coding. |
| preserve_thinking | boolean | false | - | Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's... |
| 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 to 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. |
Announcements, prompt tests, and comparisons that cover this model.
API Access How to Use the GLM 5.3 API GLM 5.3 is Z.ai's flagship coding and agentic model, with a 1M token context, always-on reasoning at three effort levels,...
Guides Kimi K3 vs GLM 5.3 vs Qwen3.8 Max vs DeepSeek V4 Pro: self-playing Flappy Bird and Missile Command We gave Kimi K3, GLM 5.3, Qwen3.8 Max 0902 and DeepSeek V4 Pro 0813 the same two coding prompts at max reasoning, one...
Guides Kimi K3 vs GLM 5.3 vs Qwen3.8 Max vs DeepSeek V4 Pro: an aquarium, a paper plane and a tiny planet We gave Kimi K3, GLM 5.3, Qwen3.8 Max 0902 and DeepSeek V4 Pro 0813 the same three coding prompts at max reasoning, one...On EmpirioLabs, GLM 5.3 is billed pay as you go: Input $1.40 per 1M prompt tokens; Output $4.40 per 1M generated tokens; Web search $0.033 per request. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.
GLM 5.3 takes Text as input and returns Text.
GLM 5.3 supports a 1M-token context window with up to 131,072 output tokens per response.
Yes. GLM 5.3 serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to glm-5-3.
Send glm-5-3 as the model in your request. The alternate IDs glm-5.3, zai/glm-5.3, zhipu/glm-5.3 also work.
Z.ai released GLM 5.3 on Aug 14, 2026.
GLM 5.3 on EmpirioLabs is served from Singapore.
Yes. The EmpirioLabs playground runs GLM 5.3 in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.
Check out our pricing or reach out if you want your own model deployed on our stack.