Skip to content
OmniRail
← All models

Z.ai · Language model

GLM Latest

~z-ai/glm-latest
  • Language
Released Aug 19, 2026

This model always redirects to the latest GLM model from Z.ai.

Specifications

Context window
1,048,576 tokens
Max output
943,718 tokens
Input
text
Output
text
Reasoning effort
max, high, low (always on)
Tokenizer
Router

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • parallel_tool_calls
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"~z-ai/glm-latest","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'