Other

Z.ai: GLM 5.2

z-ai/glm-5.2

canonical: z-ai/glm-5.2-20260616

Descriptionfrom OpenRouter

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Context length

1,048,576 tok

Max completion

943,718 tok

Knowledge cutoff

—

Expires

—

Added to OpenRouter

6/16/2026

Cache last refreshed

11/12/2026

Primary modality

text->text

Source

OpenRouter

Input modalities

text

Output modalities

text

Pricing

Field	Per token (USD)	Per million
prompt	0.000000007	$0.007
completion	0.0000068	$6.80
input_cache_read	0.000000006	$0.006

Supported parameters(21)

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Default parameters

{
  "temperature": 1,
  "top_p": 0.95,
  "top_k": null,
  "frequency_penalty": null,
  "presence_penalty": null,
  "repetition_penalty": null
}

OpenRouter page Hugging Face

Videos

21:23

Giving Qwen 3.8 27B another chance (+ GLM 5.2). Testing against GPT, Gemini, Grok etc.

Aug 18, 2026 · YouTube

Rounds

7 answersin this database. A round opens every model's answer to the same prompt.

Aug 22, 2026Home TurfSay it in Chineseround answer
Aug 18, 2026Psychology & Business AcumenThe weekend found footage movie50mediocrein a video round answer
Aug 16, 2026CodingTwo kilobytesin a video round answer
Aug 16, 2026CodingDrop the slinky95excellentin a video round answer
Aug 16, 2026CodingThe same soldierin a video round answer
Aug 16, 2026CodingThe queue that stoppedin a video round answer
Aug 16, 2026CodingTwo kilobytesin a video round answer