GLM-5.2 for roleplay Long, steady roleplay, on Ultra and Legendary.
Z.ai’s GLM-5.2 was the most used model for SillyTavern roleplay on OpenRouter in October 2026. It writes cleanly and holds its quality deep into a story, though it plays safer than GLM-5.1 and can echo your own words back. Like every storyteller on LoreWeaver, it plays inside your world with your memories and lore cards in reach, and you can switch models mid-story.
- Speed
- Fast
- Plans
- Ultra and up
- Context
- Up to 24K
GLM-5.2
Long, steady roleplay
- Context
- Ultra16K
- Legendary24K
- Released
- Jun 2026, open weights
- Public boards
- Creative writing#29 of 140
- Long stories#23 of 140
- Arena votes#33 of 414
The short answer
Is GLM-5.2 good for roleplay?
Z.ai’s GLM-5.2 was the most used model for SillyTavern roleplay on OpenRouter in October 2026. It writes cleanly and holds its quality deep into a story, though it plays safer than GLM-5.1 and can echo your own words back. It is included on Ultra at $24.99 a month, and on Legendary, with 16K to 24K tokens of context, depending on the plan. Typical reply time: about 5 to 7 seconds, measured on real LoreWeaver stories.
Updated
- About 5 to 7 seconds
- Fast
- tokens of context on its largest plan
- 24K
- the first plan that includes it
- Ultra
- the year Z.ai released it
- 2026
GLM-5.2 in play
Where it shines, and where it slips.
Strengths
- Narration: Clean, controlled writing with little purple prose and a voice that stays consistent.
- Long stories: Its quality barely slips across an eight-chapter story test.
Drawbacks
- Characters and dialogue: Tends to repeat your character’s words back and slips into therapist-style lines in emotional scenes.
- Dark themes: Tame by default, so it needs a clear push to take a story somewhere dark.
- Pacing: Less inventive than GLM-5.1 or 5.3; its plots can play it safe.
Plans and context
What each plan gives GLM-5.2.
It is included on Ultra at $24.99 a month, and on Legendary.
Context is how much the storyteller reads before it writes: the latest scenes, plus the memories, recap, and lore cards the moment needs. Bigger plans give a model more of it, which helps most in long campaigns.
| Plan | Context | Price a month |
|---|---|---|
| Ultra | 16K tokens | $24.99 |
| Legendary | 24K tokens | $49.99 |
Outside the guide
How public boards rank GLM-5.2.
None of these boards tests roleplay, so the guide reads them beside its own notes from real stories rather than in their place.
A high rank on long stories tends to mean fewer slips late in a campaign; a high arena rank means people liked its prose in a blind vote.
| Board | Rank | What it measures |
|---|---|---|
| EQ-Bench Creative Writing | 29 of 140 | Short stories from 32 prompts, compared in pairs by an AI judge (Claude Sonnet 4.6). |
| EQ-Bench Longform | 23 of 140 | A planned story eight chapters long, judged chapter by chapter and as a whole. A model that fades late loses ground. |
| Arena Creative Writing | 33 of 414 | Blind votes from people choosing the better of two answers to the same creative prompt. |
Stories it suits
Where GLM-5.2 feels at home.
Compare
Storytellers like GLM-5.2.
FAQ
GLM-5.2 questions, answered.
01Which plan includes GLM-5.2?
It is included on Ultra at $24.99 a month, and on Legendary. Every account starts free, so you can play the free storyteller first and switch models whenever you upgrade, mid-story included.
02How much context does GLM-5.2 get?
16K on Ultra, 24K on Legendary. Context is how much the model reads before it replies. LoreWeaver fills it with the latest scenes plus the memories, recap, and lore cards the moment needs, so a long story stays consistent after its opening chapters have scrolled out of view.
03How fast is GLM-5.2?
Fast: about 5 to 7 seconds for a typical reply of 150 to 300 words. That is the median of real story replies on LoreWeaver in the week to October 16, 2026, start to finish.
04Is GLM-5.2 good for dark or mature stories?
Tame by default, so it needs a clear push to take a story somewhere dark. LoreWeaver allows mature themes between adults within its published limits, and you can switch models mid-story when a scene needs a different hand.
05GLM-5.2 or GLM-5.3: which should I pick?
Pick GLM-5.2 for long, steady roleplay, and GLM-5.3 for polished, consistent stories. GLM-5.2 is fast and plays on Ultra and Legendary; GLM-5.3 is very fast and plays on Ultra and Legendary. Both keep your story’s memories and lore, so you can switch between them mid-story.
06Who makes GLM-5.2?
Z.ai makes GLM-5.2 and released it in June 2026. Its weights are public, so anyone can run it. On LoreWeaver it plays inside your world, with your lore cards, memories, and Loom threads shaping its replies.
Sources
Checked . Prices and limits change; each site’s own pages are the final word.
Your storyteller
Try GLM-5.2 in a story of your own.
Start free, then pick GLM-5.2 from the model menu once your plan includes it.