Z.ai

Browse models from Z.ai

Now Live Models

• google/gemini-3.1-pro-preview
• anthropic/claude-sonnet-4.6
• google/gemini-3-pro-image-preview

Retired Models

• Claude Sonnet 4 will be retired on June 14, 2026. Recommended upgrade to Claude Sonnet 4.6.
• Claude Opus 4: retired on May 31, 2026 (AWS Bedrock) and June 14, 2026 (Anthropic). Recommended upgrade to Claude opus 4.7.
• Qwen3 Max Thinking Preview will be deprecated on April 24, 2026. Recommended upgrade to Qwen3-Max-Thinking.
• Caution: gpt-5-chat will be deprecated on May 15, 2026 (Azure).
• Claude 3.7 Sonnet: retired on April 28, 2026 (AWS Bedrock) and May 11, 2026 (Google Cloud Vertex AI). Recommended upgrade to Claude Sonnet 4.6.

Discounts

Get 5% off service fee on top-up, exclusive gifts for referring friends.

Billing Notice

A billing anomaly was identified. Affected users will receive compensation. Read more.

Z.AI Models

Z.AI: GLM-Image

• API Request: API Request
• Chat: Chat
• 138.00K tokens

GLM-Image adopts a hybrid autoregressive + diffusion decoder architecture. It excels in text-rendering and knowledge-intensive generation.

Z.AI: GLM 4.6

• API Request: API Request
• Chat: Chat
• 1.31B tokens

GLM-4.6 is capable of handling longer code and agent tasks, with enhanced programming capabilities.

Z.AI: GLM 4.7

• API Request: API Request
• Chat: Chat
• 15.01B tokens

GLM-4.7 enhances coding capabilities, long-horizon task planning, and tool collaboration. It offers a new option that balances performance and efficiency.

Z.AI: GLM 5

• API Request: API Request
• Chat: Chat
• 30.88B tokens

GLM-5 is designed for Agentic Engineering, excelling in complex system engineering and long-range Agent tasks.

Z.AI: GLM 5.1

• API Request: API Request
• Chat: Chat
• 44.98B tokens

GLM-5.1 significantly enhances productivity in complex system engineering tasks.