Z.ai: GLM 5.2 is Z.ai's model, and its measured tokenizer sits in Z.ai's own signature group alongside its sibling models. Measured models from Undisclosed (stealth) carry the same vocabulary, which reads as reuse of Z.ai's tokenizer line and questions nobody's authorship; they are listed under "Shares this fingerprint" below.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Clean measurement; no exact match yet | tk_1d05586d |
| API surface | No other entry shares this exact contract | api_fc7114a8 |
| Context and output | 1,048,576 context · 131,072 max output | declared |
| Reasoning contract | Optional · efforts xhigh, high · default high | declared |
| Serving providers observed | Alibaba, Crusoe, Decart, DigitalOcean, Z.AI, Baidu, BaseTen, GMICloud, Sail Research | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 12 prompt tokens.
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,...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Z.ai: GLM 5.2: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
