Z.ai GLM-5.2

Released June 16, 2026. 753B-parameter open-weights MoE tuned for long-horizon agentic coding; ~$0.26/1M cached input. The open-weights price/performance leader of mid-2026.

Z.ai GLM-5.2 strengths

• Open weights
• Long-horizon agentic coding
• Strong price/performance
• 1M context
• Cheap cached input

Pricing & context

Cost guide: a typical call of ~10K input + 2K output tokens runs roughly $0.95 × 0.01 + $3.00 × 0.002 — worth modelling against cheaper tiers before committing high-volume traffic.

When to choose Z.ai GLM-5.2

Z.ai GLM-5.2 is best for Cost-efficient agentic coding and self-hosted deployments where open weights matter. If your workload is more cost-sensitive, weigh it against Llama 4 Scout (~$0.08 (varies by host) input /1M) first.

Z.ai GLM-5.2 FAQ

How much does Z.ai GLM-5.2 cost?

Z.ai GLM-5.2 is priced at $0.95 per 1M input tokens and $3.00 per 1M output tokens (public API list price), with a 1M tokens context window.

What is Z.ai GLM-5.2 best for?

Z.ai GLM-5.2 by Z.ai (Zhipu AI) is best for Cost-efficient agentic coding and self-hosted deployments where open weights matter.

Is Z.ai GLM-5.2 multimodal?

Z.ai GLM-5.2 supports text.