GLM 5.2
Z.ai · Text Generation
POST /v1/chat/completionsReasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, native web search, and tool calling.
At a glance
| Field | Value |
|---|---|
| Model id | glm-5-2 |
| Model release date | 2026-06-16 |
| Input modalities | Text |
| Output modalities | Text |
| Context window | 1M |
| Weight precision | - |
| Max output tokens | 131,072 |
| Region | Singapore |
| Features | reasoning, function_calling, web_search |
| Native inference | No |
| New | No |
| Structured output | JSON Mode |
| Supported endpoints | POST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/glm-5-2:generateContent |
| Alternate model ids | glm-5.2, zai/glm-5.2, zhipu/glm-5.2 |
Pricing
| Charge | Spec | Rate |
|---|---|---|
| Input | per 1M prompt tokens | $1.40 |
| Output | per 1M generated tokens | $4.40 |
| Web search | per request | $0.033 |
Example request
$ curl https://api.empiriolabs.ai/v1/chat/completions \ > -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ > -H 'Content-Type: application/json' \ > -d '{"model": "glm-5-2", "messages": [{"role":"user","content":"Hello"}]}'
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
max_tokens | integer | no | 65536 | Maximum number of output tokens to generate. · Range: 1 – 131072 |
temperature | number | no | 1 | Controls randomness. Lower values make responses more deterministic. · Range: 0 – 1 |
top_p | number | no | 0.95 | Nucleus sampling cutoff. · Range: 0.01 – 1 |
reasoning_effort | enum | no | "max" | GLM-5.2 reasoning effort. none disables thinking; minimal through max set how hard the model reasons before answering. max is recommended for complex coding. · Allowed: none, minimal, low, medium, high, xhigh, max |
enable_thinking | boolean | no | true | Allow the model to reason before answering. Turn off for the lowest-latency replies or strict structured output. |
do_sample | boolean | no | true | Enable sampling. Turn off for greedy deterministic output (temperature and top_p are ignored). |
tool_web_search | boolean | no | false | Enable built-in web search. Adds $0.033 per request when used. |
search_recency_filter | enum | no | "noLimit" | Limit web search results to a recency window. · Allowed: oneDay, oneWeek, oneMonth, oneYear, noLimit |
count | integer | no | 10 | Number of web search results to retrieve when web search is enabled. · Range: 1 – 50 |
search_domain_filter | string | no | - | Restrict web search to a specific domain. |
search_prompt | string | no | - | Optional prompt used to summarize retrieved web search results. |
search_result | boolean | no | true | Return web search result metadata in the response when web search is enabled. |
tool_stream | boolean | no | false | Stream function-call arguments incrementally when streaming. |
tools | array | no | [] | OpenAI-compatible function calling tool definitions. |
tool_choice | object | no | - | OpenAI-compatible tool choice control. |
stop | array | no | - | Optional stop sequences (up to 4). |
response_format | enum | no | - | Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt. |
Variants
:variant1
| Field | Value |
|---|---|
| Model id | glm-5-2:variant1 |
| Model release date | 2026-06-16 |
| Region | Germany |
| Context window | 1M |
| Weight precision | - |
| Max output tokens | 131,072 |
| Features | reasoning, function_calling, cache, web_search |
| Native inference | No |
| Structured output | JSON Schema |
| Supported endpoints | POST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/glm-5-2:variant1:generateContent |
Pricing
| Charge | Spec | Rate |
|---|---|---|
| Input | per 1M prompt tokens | $1.10 (was $1.40) |
| Output | per 1M generated tokens | $3.851 (was $4.40) |
| Implicit cache read | per 1M cached input tokens | $0.275 |
| Web Search (Linkup) | per call when invoked | $0.013 |
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
temperature | number | no | 0.7 | Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2 |
top_p | number | no | 0.9 | Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1 |
max_tokens | number | no | 4096 | Maximum output tokens. · Range: 1 – 131072 |
stop | string | no | - | Up to 4 strings where the model will stop generating further tokens. |
enable_thinking | boolean | no | true | Enable step-by-step reasoning before answering. |
reasoning_effort | enum | no | "medium" | Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service. · Allowed: none, low, medium, high, max |
thinking_budget | number | no | 32768 | Maximum tokens reserved for the reasoning process. Up to 131072. · Range: 1 – 131072 |
response_format | enum | no | - | Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide. |
web_search_linkup | boolean | no | false | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default. |
disable_formatting | boolean | no | false | When enabled, the gateway will not append the “Sources” footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration. |
Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/glm-5-2.