GLM-5.3

GLM-5.3 is Z.ai’s open-weights reasoning model for coding and long-running agent tasks. Prime Inference serves z-ai/glm-5.3 on Prime GPU infrastructure as a hosted model.

	GLM-5.3 on Prime Inference
Model ID	`z-ai/glm-5.3`
Context window	1,048,576 tokens
Maximum output	131,072 tokens
Input and output	Text
Reasoning	Always enabled; `low`, `high`, or `max` effort (default `max`)

See the model catalog or the Models API for current pricing and availability. Other GLM variants have different capabilities and serving providers.

Use Prime Inference

Create a Prime API key with Inference permission in the API keys guide, then run:

export PRIME_API_KEY="your-api-key"

curl https://api.pinference.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $PRIME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3",
    "messages": [{"role": "user", "content": "Explain this codebase in three sentences."}]
  }'

To charge a team instead of your personal account, add -H "X-Prime-Team-ID: your-team-id". See the Inference quickstart for Python SDK setup and billing details. Keep API keys server-side.

Getting Started

Lab

Inference

Model Factory

Libraries

Compute

Use Prime Inference

​Use Prime Inference

Use Prime Inference