Z.ai GLM 5.2 on OpenRouter

pip install zai-sdk # Or specify version pip install zai-sdk== 0.2.3 Verify Installation import zai print (zai. __version__ ) Basic Call from zai import ZaiClient client = ZaiClient( api_key = "your-api-key" ) # Your API Key response = client.chat.completions.create( model = "glm-5.2" , messages = [ { "role" : "system" , "content" : "You are a senior full-stack software engineer, proficient in frontend development, backend architecture design, and modern web technology stacks." , }, { "role" : "user" , "content" : "Design and build a personal blog website for me, including a homepage, article list page, and article detail page, using React + Node.js technology stack." , }, ], thinking = { "type" : "enabled" , }, reasoning_effort = "max" , max_tokens = 4096 , temperature = 1.0 , ) # Get complete response print (response.choices[ 0 ].message) Streaming Call from zai import ZaiClient client = ZaiClient( api_key = "your-api-key" ) # Your API Key response = client.chat.completions.create( model = "glm-5.2" , messages = [ { "role" : "system" , "content" : "You are a senior full-stack software engineer, proficient in frontend development, backend architecture design, and modern web technology stacks." , }, { "role" : "user" , "content" : "Design and build a personal blog website for me, including a homepage, article list page, and article detail page, using React + Node.js technology stack." , }, ], thinking = { "type" : "enabled" , # Optional: "disabled" or "enabled", default is "enabled" }, reasoning_effort = "max" , stream = True , max_tokens = 4096 , temperature = 0.6 , ) # Stream response for chunk in response: if chunk.choices[ 0 ].delta.reasoning_content: print (chunk.choices[ 0 ].delta.reasoning_content, end = "" , flush = True ) if chunk.choices[ 0 ].delta.content: print (chunk.choices[ 0 ].delta.content, end = "" , flush = True ) Install SDK Maven < dependency > < groupId > ai.z.openapi </ groupId > < artifactId > zai-sdk </ artifactId > < version > 0.3.5 </ version > </ dependency > Gradle (Groovy) implementation &#x27;ai.z.openapi:zai-sdk:0.3.5&#x27; Basic Call import ai.z.openapi.ZaiClient; import ai.z.openapi.service.model.ChatCompletionCreateParams; import ai.z.openapi.service.model.ChatCompletionResponse; import ai.z.openapi.service.model.ChatMessage; import ai.z.openapi.service.model.ChatMessageRole; import ai.z.openapi.service.model.ChatThinking; import java.util.Arrays; public class BasicChat { public static void main ( String [] args ) { // Initialize client ZaiClient client = ZaiClient . builder (). ofZAI (). apiKey ( "your-api-key" ). build (); // Create chat completion request ChatCompletionCreateParams request = ChatCompletionCreateParams . builder () . model ( "glm-5.2" ) . messages ( Arrays . asList ( ChatMessage . builder () . role ( ChatMessageRole . SYSTEM . value ()) . content ( "You are a senior full-stack software engineer, proficient in frontend development, backend architecture design, and modern web technology stacks." ) . build (), ChatMessage . builder () . role ( ChatMessageRole . USER . value ()) . content ( "Design and build a personal blog website for me, including a homepage, article list page, and article detail page, using React + Node.js technology stack." ) . build ())) . thinking ( ChatThinking . builder (). type ( "enabled" ). build ()) . reasoningEffort ( "max" ) . maxTokens ( 4096 ) . temperature ( 1.0f ) . build (); // Send request ChatCompletionResponse response = client . chat (). createChatCompletion (request); // Get response if ( response . isSuccess ()) { Object reply = response . getData (). getChoices (). get ( 0 ). getMessage (); System . out . println ( "AI Response: " + reply); } else { System . err . println ( "Error: " + response . getMsg ()); } } } Streaming Call import ai.z.openapi.ZaiClient; import ai.z.openapi.service.model.ChatCompletionCreateParams; import ai.z.openapi.service.model.ChatCompletionResponse; import ai.z.openapi.service.model.ChatMessage; import ai.z.openapi.service.model.ChatMessageRole; import ai.z.openapi.service.model.ChatThinking; import ai.z.openapi.service.model.Delta; import java.util.Arrays; public class StreamingChat { public static void main ( String [] args ) { // Initialize client ZaiClient client = ZaiClient . builder (). ofZAI (). apiKey ( "your-api-key" ). build (); // Create streaming chat completion request ChatCompletionCreateParams request = ChatCompletionCreateParams . builder () . model ( "glm-5.2" ) . messages ( Arrays . asList ( ChatMessage . builder () . role ( ChatMessageRole . SYSTEM . value ()) . content ( "You are a senior full-stack software engineer, proficient in frontend development, backend architecture design, and modern web technology stacks." ) . build (), ChatMessage . builder () . role ( ChatMessageRole . USER . value ()) . content ( "Design and build a personal blog website for me, including a homepage, article list page, and article detail page, using React + Node.js technology stack." ) . build ())) . thinking ( ChatThinking . builder (). type ( "enabled" ). build ()) . reasoningEffort ( "max" ) . stream ( true ) // Enable streaming output . maxTokens ( 4096 ) . temperature ( 1.0f ) . build (); ChatCompletionResponse response = client . chat (). createChatCompletion (request); if ( response . isSuccess ()) { response . getFlowable () . subscribe ( // Process streaming message data data -> { if ( data . getChoices () != null && ! data . getChoices (). isEmpty ()) { Delta delta = data . getChoices (). get ( 0 ). getDelta (); System . out . print (delta + " \n " ); } }, // Process streaming response error error -> System . err . println ( " \n Stream error: " + error . getMessage ()), // Process streaming response completion event () -> System . out . println ( " \n Streaming response completed" )); } else { System . err . println ( "Error: " + response . getMsg ()); } } } Install SDK # Install or upgrade to latest version pip install --upgrade &#x27;openai>=1.0&#x27; Verify Installation python - c "import openai; print(openai.__version__)" Usage Example from openai import OpenAI client = OpenAI( api_key = "your-Z.AI-api-key" , base_url = "https://api.z.ai/api/paas/v4/" , ) completion = client.chat.completions.create( model = "glm-5.2" , messages = [ { "role" : "system" , "content" : "You are a senior full-stack software engineer, proficient in frontend development, backend architecture design, and modern web technology stacks." }, { "role" : "user" , "content" : "Design and build a personal blog website for me, including a homepage, article list page, and article detail page, using React + Node.js technology stack." , }, ], ) print (completion.choices[ 0 ].message.content) Was this page helpful? Yes No Migrate to GLM-5.2 GLM-5.1 ⌘ I x github discord linkedin Powered by This documentation is built and hosted on Mintlify, a developer documentation platform