Z.ai · text model

GLM-5.3

#14 of 31 text models on overall (provisional). $3.86 per 1,000 support replies at list price.

Price checked 25 Oct 2026 via OpenRouter
key_facts.txt
Released
14 Aug 2026
Context window
1M tokens
Longest reply
131K tokens
Open weights
Yes
Reasoning mode
Yes
Tool use
Yes
Reads
text
Writes
text
Knowledge cutoff
–
scores.txt
Overall61
Writing70
Support67
Coding68
Value54
Provisional, 0 to 100 among the text models we track, from Arena and Epoch AI. How we score.

Prices and where to run it

ProviderRegionInput per 1MOutput per 1MCached inputData retentionChecked
openrouterglobal$0.079$1.40$0.078Not checked25 Oct 2026, OpenRouter
zaiglobal$1.40$4.40$0.26Not checkedList price, unverified

Price history and a CSV download arrive with the open price dataset.

Benchmarks behind the scores

MeasureFigureRun dateSource
Epoch Capabilities Index15625 Oct 2026Epoch AI
Arena text, coding1497.722 Oct 2026Arena
Arena text, creative writing1459.222 Oct 2026Arena
Arena text, instruction following1480.322 Oct 2026Arena
Arena text, multi-turn1469.922 Oct 2026Arena
Arena text, overall1473.922 Oct 2026Arena
Arena WebDev1622.823 Oct 2026Arena
call_it.sh
Call it through OpenRouter
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "z-ai/glm-5.3", "messages": [{"role": "user", "content": "Hello"}]}'
next.txt
Compare and switchAlternatives to GLM-5.3 →GLM-5.3 vs GPT-5.6 Terra →Work out your monthly cost →

What changed

alerts.txt
Model Menu will email you about this, plus the Friday letter. One click unsubscribes. We never sell or share your address.