Skip to main content
GLM-5.3 is Z.ai’s model for reasoning, coding, and tool use, with a 262K context window. It thinks before it answers and shows that reasoning ahead of the final answer. It supports function calling and JSON output, and works with the OpenAI SDK.

Try in playground

Test GLM-5.3 in the Runpod Hub playground.
This endpoint is compatible with the OpenAI API. See the OpenAI compatibility examples below.

Request

All parameters are passed within the input object in the request body.
string
required
The prompt to send to the model.
string
default:"You are a helpful assistant."
System prompt that sets the model’s behavior.
array
Array of message objects with role and content, for multi-turn conversations.
string
required
The role of the message author. Use system, user, or assistant.
string
required
The content of the message.
string
default:"glm-5.3"
required
The model to use. The only option is glm-5.3.
float
default:"1"
Sampling temperature. Lower values make output more deterministic. Range: 0-2.
float
Nucleus sampling threshold. Range: 0.0-1.0.
integer
default:"4096"
Maximum number of tokens to generate. Reasoning tokens count toward this limit. Range: 1-131,072.
string
default:"low"
How much the model thinks before it answers. Options: low, medium, high. Thinking can’t be turned off.
array
Stop sequences that halt generation.

Response

string
Unique identifier for the request.
string
Request status. Returns COMPLETED on success, FAILED on error.
integer
Time in milliseconds the request spent in queue before processing began.
integer
Time in milliseconds the model took to generate the response.
object
The generation result, including the generated text, the cost in USD, and token usage.

OpenAI API compatibility

GLM-5.3 is compatible with the OpenAI API format. Use the OpenAI Python client with the endpoint’s base URL and your Runpod API key:
Python (OpenAI SDK)
For streaming responses, add stream=True:
Python (Streaming)
GLM-5.3 reasons before it answers, and reasoning tokens count toward max_tokens. If answers are cut off, raise max_tokens.

Cost calculation

GLM-5.3 charges separate rates for input and output tokens: $0.77 per 1M input tokens, $2.42 per 1M output tokens, and $0.143 per 1M cached input tokens.
Last modified on November 14, 2026