DoublewordDoubleword

Model Name

zai-org/GLM-5.3

GLM 5.3

  • Type: Generation
  • Capabilities: reasoning, enhanced_structured_generation
  • Cache read: $0.28 per 1M input tokens (0.2× standard input price). See prompt caching.

Overview

GLM 5.3 is Z.ai's open-weight reasoning model for complex coding, long-horizon agentic work, tool use, cybersecurity analysis and repository-scale engineering. It provides a 1M-token context window and configurable reasoning effort.

Pricing

PriorityInput Tokens (per 1M)Cache Read Tokens (per 1M)Output Tokens (per 1M)
Realtime1$1.40$0.28$4.40
Async$1.05$0.21$3.30
Batch (24h)$0.70$0.14$2.20

Playground

Open this model in the Playground.

Footnotes

  1. Realtime availability is limited. Doubleword is primarily a batch API.