GLM 5.3: API price, context window and how to connect

GLM 5.3 by Z.ai (Zhipu): $0.079 per million input tokens, $1.4 per million output tokens, a 1.05M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

Updated Copy as Markdown
In this article

In short#

A large reasoning model from Z.ai (Zhipu) for complex software engineering and long agentic tasks. Text in and out, a 1-million-token window. The weights are open.

Specifications#

Provider Z.ai (Zhipu)
Released 2026-08-18
Context window 1.05M tokens
Accepts text
Answers with text
Reasoning mode yes
Tool calling yes
Open weights yes
Identifier z-ai/glm-5.3

Price#

Per 1M tokens In dollars
Input (question, context) $0.079
Output (answer) $1.4

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.023. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

What it is good for#

  • Complex development
  • Long agentic tasks
  • Cheap input with long context

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
Qwen3.7 Plus $0.32 $1.28 1M 1.2× more expensive
Llama 4 Maverick $0.188 $0.652 1.05M 1.6× cheaper
Qwen3.8 27B $0.24 $2.2 1M 1.7× more expensive
Devstral 2 2512 $0.4 $2 262K 1.7× more expensive
DeepSeek V3.2 $0.28 $0.42 164K 1.8× cheaper

Other Z.ai (Zhipu) models#

How to connect in SKILLOK#

GLM 5.3 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the z-ai/glm-5.3 model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.

Where the data comes from#

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

Was this helpful?