GLM 5.3

Z.ai· released 18 Aug 2026

z-ai/glm-5.3
Input / 1M tokens
$1.4
Output / 1M tokens
$4.4
Context window1M tokens

Longest answer: 131K tokens

reads textopen weightstool callingreasoning

About

GLM 5.3 is a Z.ai reasoning model for complex software engineering and long-horizon agent tasks, according to its summary. It accepts and outputs text, supports tools, and has open weights. Its context window is 1,048,576 tokens, with a maximum output of 131,072 tokens. The model id is z-ai/glm-5.3, and its Hugging Face id is zai-org/GLM-5.3. Pricing is USD 1.4 per 1M input tokens and USD 4.4 per 1M output tokens. Z.ai released it on 2026-08-18. The summary says the model improves, but does not state what it improves or give a comparison, so that claim does not establish a specific capability beyond the listed focus on software engineering and agent tasks.

Who it is for

GLM 5.3 may suit teams building text-based software engineering or agent workflows that need tools and a long context window. Its open weights and per-million-token rates are listed for evaluation and budgeting.

What is good

  • Open weights
  • 1,048,576-token context window
  • Supports tools and reasoning
  • Focuses on software engineering and agent tasks

What to know first

  • Accepts text input only
  • Costs USD 1.4 per 1M input tokens
  • Costs USD 4.4 per 1M output tokens

Verdict

GLM 5.3 offers open weights, tool support, and a context window exceeding one million tokens. Its listed token rates and text-only input are important fit considerations.

Details

Lab
Z.aiopenrouter.ai · 3 Oct 2026
Context
1,049Kopenrouter.ai · 3 Oct 2026
Input price
$1.4 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$4.4 / 1Mopenrouter.ai · 3 Oct 2026
Max output
131,072 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list