• Playground
  • Models
  • Rankings
  • Support

All systems operational

Zero data retentionYour prompts and outputs are never stored or trained on

© 2026 BoundlessTermssupport@boundless.network
All models

GLM-5.3

by Z.ai ~ Long-running coding agents that need a million-token context

GLM-5.3 is Z.AI's 753-billion-parameter mixture-of-experts flagship, with a sparse-attention design that keeps long prompts affordable. It always thinks, and reasoning effort can be set to low, high, or max.

Its 1,048,576-token context window suits coding agents that carry a large repository and long tool traces. Z.AI reports stronger agentic coding results than GLM-5.2 at a lower token cost per task.

1M context
  • Text
  • Reasoning
  • Tool use
Model weights
glm-5.3Try it in the playground

Pricing

Pricing
USD per 1M tokens.
WindowInputCached inputOutput
asap$1.12$0.14$3.52
What one request costs
Prompt94Ktokens
Cached prefix66Ktokens
Reply2Ktokens

$0.0461

per request to GLM-5.3

Prompt
68.5%
Cached
20%
Reply
11.5%

GLM-5.3: $0.046076 per request

94,000 prompt tokens, 65,800 of them cached, and 1,500 reply tokens.

The same request, across other models