GLM-5.2
GLM-5.2 is available now for coding, rag, and agents with 1m context; evaluate it while provider pricing coverage matures.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 1m context window
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Teams that need a tracked hosted API route today
- Family
- GLM-5
- Released
- 2026-06-13
- Context
- 1m
- Max output
- 131,072
- Parameters
- 744B total, 40B active
- Architecture
- Mixture of Experts
- Specialization
- coding
- License
- Unknown / Unverified
- Training
- Fine-tuned
No tracked provider token pricing is available yet.
About
GLM-5.2 is Z.ai's coding-first successor to GLM-5.1 in the GLM-5 family. It is available through the GLM Coding Plan and supports a promoted 1M-token context variant via the glm-5.2[1m] model ID suffix, with a 131,072-token maximum output and high/max thinking-effort levels for coding agents. Source-backed provider pricing, public benchmark scores, standalone token API rows, and downloadable GLM-5.2 MIT weights were not yet available as of June 15, 2026, so this seed row tracks the model while leaving provider, benchmark, and open-weight metadata empty until those launch details are verified.
GLM-5.2 is a model in the GLM-5 family. The structured metadata tracks a 1m-token context window, reasoning, function calling, tool use, structured outputs, and code execution. No headline benchmark score is tracked for GLM-5.2 yet.
Top use-case fit: coding, agents, and build tasks
Coding
Included by capability and metadata signals in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.