Hydedocs

Models

The models the gateway serves, with their limits.

hyde/glm-5.2
Deep-reasoning model
  • Context window: 1,048,576 tokens (includes prompt + output) · Max output: 131,072 tokens
  • Deep reasoning at full context
  • Best for: hard problems, architecture, long analysis
hyde/glm-5.3-flash
Fast everyday model
  • Context window: 1,048,576 tokens (includes prompt + output) · Max output: 131,072 tokens
  • Entire codebases in one prompt
  • Best for: everyday chat, edits, quick answers
hyde/kimi-k3
Vision · long-context model
  • Context window: 1,048,576 tokens (includes prompt + output) · Max output: 1,048,576 tokens (default 131,072)
  • Reads images as well as text
  • Best for: reading, image-heavy work, long documents
Was this page helpful?