GLM 5.1

Z.ai released 2026-04-07

$1.48 per million tokens, balanced

DeepSeek V4 Flash 0731 is both better and cheaper.

It scores +10.8 higher and costs 93% less ($0.105/M against $1.48/M) on this workload — and it does everything this model does.

Gemini 3.7 Flash is cheaper still (49% less) but drops 128K → 66K max output.

Every price dimension

Input$0.966/M
Output$3.04/M
Cached input$0.179/M

Independent scores

Intelligence41
Coding55.8
Agentic30.6
LMArena Elo1464.1default

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

  • dataviz #3of 142 1366
  • agenticslides #3of 16 1245
  • agenticslides(python-pptx) #4of 16 1240
  • pptxslides #4of 14 1241
  • python-pptxslides #5of 35 1258
  • agentichtmlslides #6of 16 1205
  • agenticslides(html) #6of 16 1204
  • 3d #8of 136 1336

Capability

Context window205K
Max output128K
Input modestext
Tool useyes
Reasoningoptional

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

Markdown for LLMs