GLM 5.2

Z.ai released 2026-06-16 mit

$1.48 per million tokens, balanced

Gemini 3.7 Flash scores higher and costs less — but you would give something up.

+3.4 on the capability index and 49% cheaper ($0.750/M against $1.48/M). What you lose:

  • 131K → 66K max output

Capability scores do not measure context length, output ceiling or which inputs a model accepts, so a higher score does not mean a drop-in replacement.

The same model via free is 100% cheaper (free/M) — same weights, different latency.

Every price dimension

Input$0.966/M
Output$3.04/M
Cached input$0.193/M

Independent scores

Intelligence52.6
Coding68.8
Agentic45.7
LMArena Elo1465.4max

Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.

Best rankings by task

  • website #4of 151 1326
  • codecategories #6of 145 1331
  • dataviz #7of 142 1324
  • 3d #7of 136 1347
  • uicomponent #9of 140 1328
  • fullstack #10of 59 1269
  • agenticgamedev #10of 34 1187
  • htmlslides #10of 34 1190

Capability

Context window1.0M
Max output131K
Input modestext
Tool useyes
Reasoningoptional
Open weightsyes

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified
Cross-checkedvendor page

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,...

Markdown for LLMs