Skip to main content
Z.aiJun 16, 2026

GLM 5.2

zai-org-glm-5-2PrivateOpen weights

GLM-5.2, the successor to GLM-5.1, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports a longer context window than GLM-5.1 for processing extensive text and detailed analysis with fast inference speed.

$1.40/$4.40
per 1M in / out
1M
context window
128K
max output
Also available end-to-end encrypted$1.75 / $5.75 per 1M
How it comparesamong 143 text models
GPQA Diamondhigher than 22%71.2%
Blended pricecheaper than 44%$2.15
Context windowlarger than 42%1M
Max outputlarger than 78%128K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_formatReasoningreasoning_effort none · high · max
Web searchenable_web_search
Prompt cachingReads at $0.26
Optimized for codeTuned for software work

Not supportedimage input, video input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
71.2%107th of 139 · 52 score higher for less, including Gemini 3.8 Flash, Gemini 3.7 Flash and Pareto

Specs

Model ID
zai-org-glm-5-2
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
131,072 tokens
Reasoning
none · high · max · default max
Precision
FP8
Privacy
Private
Added
Jun 16, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
GLM 5.2$1.40$4.4071.2%1M128K——
DeepSeek V4 Pro$1.65$3.3082.8%1M256K——
Gemini 3.6 Flash$0.9375$4.6980.3%1M64K——
Gemini 3.7 Flash$0.9375$4.6995.5%1M64K——
DeepSeek V4 Pro 0813$1.65$4.9582.3%1M256K——

Other versions

  1. GLM 4.6Apr 2024
  2. GLM 4.7Dec 2025
  3. GLM 5Feb 2026
  4. GLM 5.1Apr 2026
  5. GLM 5.2Jun 2026
  6. GLM 5.3Aug 2026

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$1.40per 1M tokens
Cached input$0.2681% off input
Output$4.40per 1M tokens

Estimate a workload

$0.005per request
$50.00for 10,000 requests

Blended price against similar models

GLM 5.2$2.15

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zai-org-glm-5-2",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "max"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelzai-org-glm-5-2Required
messagestextContent parts the model reads
max_completion_tokensUp to 131,072Counts reasoning tokens
reasoning_effortnone | high | maxDefault max
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations