Z.AI
GLM-5.2
Open flagship GLM for long-horizon coding agents and million-token context work
Model facts
- Context window
- 1M tokens
- Maximum output
- 131K tokens
- Cheapest paid input
- $0.3 per 1M tokens
- Cheapest paid output
- $1.05 per 1M tokens
- Open weights
- yes
- Providers
- 101
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image.
Local hardware estimate
At 4K context: Q4_K_M 462.1 GiB, Q8_0 812.8 GiB, F16 1470.6 GiB working memory.
- Parameters
- 753.3 billion
- Architecture
- glmmoedsa
- Model license
- mit
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| max | 52.6 | 68.8 | not measured | 68.6 |
| Non-reasoning | 34.8 | 46.5 | not measured | 93.4 |
Observed price history
- 2026-08-24: $0.3 input / $1.05 output per 1M tokens
API providers
- Alibaba Token Plan — model id glm-5.2; free input / free output per 1M tokens; provider documentation
- Alibaba Token Plan (China) — model id glm-5.2; free input / free output per 1M tokens; provider documentation
- Kenari — model id glm-5-2; free input / free output per 1M tokens; provider documentation
- NaN — model id glm5.2; free input / free output per 1M tokens; provider documentation
- Nvidia — model id z-ai/glm-5.2; free input / free output per 1M tokens; provider documentation
- OpenRouter — model id z-ai/glm-5.2:free; free input / free output per 1M tokens; provider documentation
- SCNet Token Plan — model id GLM-5.2; free input / free output per 1M tokens; provider documentation
- SenseNova (China) — model id glm-5.2; free input / free output per 1M tokens; provider documentation
- Umans AI Coding Plan — model id umans-glm-5.2; free input / free output per 1M tokens; provider documentation
- UnoRouter — model id glm-5.2:free; free input / free output per 1M tokens; provider documentation
- Z.AI Coding Plan — model id glm-5.2; free input / free output per 1M tokens; provider documentation
- ZenMux — model id z-ai/glm-5.2-free; free input / free output per 1M tokens; provider documentation
- Zhipu AI Coding Plan — model id glm-5.2; free input / free output per 1M tokens; provider documentation
- CrofAI — model id glm-5.2; $0.3 input / $1.05 output per 1M tokens; provider documentation
- NanoGPT — model id z-ai/glm-5.2; $0.42 input / $1.32 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id glm-5.2; $0.55 input / $1.78 output per 1M tokens; provider documentation
- LLM Gateway (SCX.ai) — model id scx-ai-gp/glm-5.2; $0.55 input / $1.78 output per 1M tokens; provider documentation
- SCX.ai — model id GLM-5.2; $0.55 input / $1.78 output per 1M tokens; provider documentation
- Ambient — model id z-ai/glm-5.2; $0.6 input / $2 output per 1M tokens; provider documentation
- DigitalOcean — model id glm-5.2; $0.7 input / $2.2 output per 1M tokens; provider documentation
- Inceptron — model id zai-org/GLM-5.2; $0.71 input / $2.35 output per 1M tokens; provider documentation
- Deep Infra — model id zai-org/GLM-5.2; $0.75 input / $2.4 output per 1M tokens; provider documentation
- Weights & Biases — model id zai-org/GLM-5.2; $0.76 input / $2.42 output per 1M tokens; provider documentation
- routing.run — model id glm-5.2; $0.8 input / $2.4 output per 1M tokens; provider documentation
- LLM Gateway (Runware) — model id runware/glm-5.2; $0.8 input / $2.55 output per 1M tokens; provider documentation
- Requesty — model id glm-5.2; $0.8 input / $2.55 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id zai/glm-5.2; $0.8 input / $2.55 output per 1M tokens; provider documentation
- Lilac — model id zai-org/glm-5.2; $0.9 input / $3 output per 1M tokens; provider documentation
- Vultr — model id zai-org/GLM-5.2-FP8; $0.85 input / $3.1 output per 1M tokens; provider documentation
- OpenRouter — model id z-ai/glm-5.2; $0.966 input / $3.04 output per 1M tokens; provider documentation
- GMI Cloud — model id zai-org/GLM-5.2-FP8; $0.979 input / $3.08 output per 1M tokens; provider documentation
- Ofox — model id z-ai/glm-5.2; $0.98 input / $3.08 output per 1M tokens; provider documentation
- Merge Gateway — model id zai/glm-5.2; $1.05 input / $3.3 output per 1M tokens; provider documentation
- Alibaba (China) — model id glm-5.2; $1.1 input / $3.85 output per 1M tokens; provider documentation
- ai& — model id zai-org/glm-5.2; $1 input / $4 output per 1M tokens; provider documentation
- AIHubMix — model id glm-5.2; $1.13 input / $3.94 output per 1M tokens; provider documentation
- DInference — model id glm-5.2; $1.25 input / $3.89 output per 1M tokens; provider documentation
- LLM Gateway (EmberCloud) — model id embercloud/glm-5.2; $1.26 input / $3.96 output per 1M tokens; provider documentation
- Wafer — model id GLM-5.2; $1.2 input / $4.1 output per 1M tokens; provider documentation
- Volcengine Ark — model id glm-5-2-260617; $1.19 input / $4.16 output per 1M tokens; provider documentation
- Ambient — model id zai-org/GLM-5.2-FP8; $1.2 input / $4.2 output per 1M tokens; provider documentation
- Cortecs — model id glm-5.2; $1.2 input / $4.2 output per 1M tokens; provider documentation
- Requesty (EU) — model id glm-5.2@eu; $1.2 input / $4.2 output per 1M tokens; provider documentation
- Vivgrid — model id glm-5.2; $1.2 input / $4.2 output per 1M tokens; provider documentation
- CrossModel — model id z-ai/glm-5.2; $1.2 input / $4.4 output per 1M tokens; provider documentation
- Abacus — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Alibaba — model id glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Arcee — model id zai-org/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Baseten — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- ClinePass — model id cline-pass/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Cloudflare Workers AI — model id @cf/zai-org/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Crusoe — model id zai/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Databricks — model id databricks-glm-5-2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Eden AI — model id zai/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- EmpirioLabs AI — model id glm-5-2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Fireworks AI — model id accounts/fireworks/models/glm-5p2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Friendli — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- HPC-AI — model id zai-org/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Hugging Face — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Impossibl — model id fireworks/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Impossibl — model id zai/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Jalapeno Cloud — model id GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Kilo Gateway — model id z-ai/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- LLM Gateway (Alibaba Cloud) — model id alibaba/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- LLM Gateway (Baidu) — model id baidu/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- LLM Gateway (ByteDance) — model id bytedance/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- LLM Gateway (CanopyWave) — model id canopywave/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- LLM Gateway (NovitaAI) — model id novita/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- LLM Gateway (Z AI) — model id zai/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Mistral — model id zai-glm-5-2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Nebius Token Factory — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Neon — model id glm-5-2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- NovitaAI — model id zai-org/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- OpenCode Go — model id glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- OpenCode Zen — model id glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- OrcaRouter — model id z-ai/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Pioneer — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- SiliconFlow — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- SiliconFlow (China) — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Subconscious — model id subconscious/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Synthetic — model id hf:zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Together AI — model id zai-org/GLM-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- TokenGo — model id z-ai/glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Umans AI — model id umans-glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Venice AI — model id zai-org-glm-5-2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Z.AI — model id glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- Zhipu AI — model id glm-5.2; $1.4 input / $4.4 output per 1M tokens; provider documentation
- ZenMux — model id z-ai/glm-5.2; $1.4 input / $4.5 output per 1M tokens; provider documentation
- Neuralwatt — model id glm-5.2; $1.45 input / $4.5 output per 1M tokens; provider documentation
- TensorX — model id z-ai/glm-5.2; $1.5 input / $4.5 output per 1M tokens; provider documentation
- GreenPT — model id glm-5.2; $1.25 input / $5.02 output per 1M tokens; provider documentation
- Charm Hyper — model id glm-5.2; $1.52 input / $4.79 output per 1M tokens; provider documentation
- Berget.AI — model id zai-org/GLM-5.2; $1.54 input / $4.84 output per 1M tokens; provider documentation
- above.dev — model id glm-5.2; $1.54 input / $4.84 output per 1M tokens; provider documentation
- UnoRouter — model id glm-5.2; $1.6 input / $5.03 output per 1M tokens; provider documentation
- evroc — model id zai-org/GLM-5.2; $1.44 input / $5.75 output per 1M tokens; provider documentation
- Scaleway — model id glm-5.2; $1.8 input / $5.5 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id glm-5.2-fast; $1.99 input / $6.16 output per 1M tokens; provider documentation
- Regolo AI — model id glm5.2; $2.31 input / $6 output per 1M tokens; provider documentation
- Model Oracle AI — model id glm-5.2; not published input / not published output per 1M tokens; provider documentation
- Ollama Cloud — model id glm-5.2; not published input / not published output per 1M tokens; provider documentation