Standard Compute
← All models

GLM 5.2

Frontier

Z.AI's flagship open-weight model — strong agentic coding with a 1M context.

Z.AI
Maker
89/100
Overall
74
Value score
$1.26
Blended /1M
1.0M
Context
Open
Weights
Pricing: $0.77 in · $2.42 out / 1M tokens · synced from OpenRouter · updated 2026-08-02

Scorecard

Output Quality9.0/10 · 77% community
Agentic Ability9.2/10 · 78% community
Speed7.6/10 · 71% community
Value for $8.8/10 · 76% community
Reliability8.7/10 · 76% community

GLM 5.2 is Z.AI's flagship open-weight model and the latest in a GLM line that became hugely popular for coding agents. It pairs strong agentic coding with a 1M-token context at open-weight pricing.

Strengths
  • Strong agentic coding
  • Open weights
  • 1M context
Trade-offs
  • Just behind the closed flagships on hard tasks
  • Hosted throughput varies

Agents that run GLM 5.2 well

Open-weight coding agents that want a long context.

Best model for ClineBest model for AiderBest model for Kilo CodeBest model for OpenCodeBest model for OpenClaw

GLM 5.2 FAQ

Is GLM 5.2 good for AI agents?
Open-weight coding agents that want a long context. On our editorial scoring it rates 9.2/10 for agentic ability and 9.0/10 for output quality. Strong agentic coding.
How much does GLM 5.2 cost?
Via OpenRouter, GLM 5.2 is priced at $0.77 in · $2.42 out / 1M tokens — a blended rate of about $1.26 per 1M tokens for typical input-heavy agent use.
What is GLM 5.2's context window?
GLM 5.2 has a 1.0M-token context window — large enough to hold sizeable codebases or document sets in a single run. Z.AI is the maker.
Is GLM 5.2 open source?
Yes — GLM 5.2 ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of GLM 5.2?
The main trade-offs: just behind the closed flagships on hard tasks; hosted throughput varies. It's strongest for open-weight coding agents that want a long context.

GLM 5.2 compared

GLM 5.2 vs Fable 5GLM 5.2 vs SolGLM 5.2 vs Opus 4.8GLM 5.2 vs GPT-5.5GLM 5.2 vs Gemini 3.1 ProGLM 5.2 vs Qwen3.7 MaxGLM 5.2 vs DeepSeek V4 ProGLM 5.2 vs Kimi K2.6

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Fable 5 · GPT-5.6 Sol

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. No usage limits. One flat bill.

Free trial · no card · plans from $39/mo

Free trial No credit card needed Billing by Stripe4,900+ agent users