API Reference

GLM

GLM models are general-purpose chat and reasoning models.

Models

Model	Code	Notes
GLM 5.3	glm-5.3	Latest flagship; stronger software engineering and agent capabilities.
GLM 5.3 Flash	glm-5.3-flash	Cost-efficient; first natively multimodal GLM-5 model.
GLM 5.2	glm-5.2	Previous generation.

Capabilities

• tools, tool_choice
• temperature, top_p, max_tokens, response_format

See Parameter Support by Model for the full matrix.

Example

from openai import OpenAI

client = OpenAI(base_url="https://llm.siraya.ai/v1", api_key="<API_KEY>")
resp = client.chat.completions.create(
    model="glm-5.3",
    messages=[{"role": "user", "content": "Give me three startup ideas."}],
)
print(resp.choices[0].message.content)