Identity
- Status
- active
- Developer ID
zai-org/GLM-5.2- Released
- Not reported
- Version
- GLM-5.2
- License
- mit
Z.aiGLM 5.2
GLM-5.2 is an open-weight language model published by Z.ai.
- Token context
- 1,049K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Not reported
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.75 | $2.40 | $0.14 | — | Oct 19, 2026 | Provider-reported |
 OpenrouterAvailable | $1.19 | $3.74 | $0.221 | — | Aug 28, 2026 | Provider-reported |
Benchmarks
All benchmark results →| LiveBench2026-06-25-90f8d44da965 | 76.96 | 23,463 | 1,270 | glm-5.2average per case | Recomputedwinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,470.37 | — | 49,820 | glm-5.2-max; 95% CI [1466.22224854, 1474.51957977]; votes 49820; rank 31unknown | Original sourcewinner eligible | Third-party benchmark |
| ToneBench2026-10-17-10-task-e9c76358afb2 | 75.76 | 11,138 | 50 | GLM-5.2 (high)average per case | Original sourcenot winner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 1,049K tokens
- Maximum output
- Unknown
- Total parameters
- 753.3B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliaseszai-org/GLM-5.2, zai-org/GLM-5.2
Explicit Unknowns
- Release date
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
zai-org/GLM-5.2 developer model repositoryZ.ai · observed Aug 28, 2026Deepinfra catalogDeepinfra · observed Oct 19, 2026OpenRouter z-ai/glm-5.2 model APIOpenRouter · observed Aug 28, 2026zai-org/GLM-5.2 Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026zai-org/GLM-5.2 config.json at b4734de4facfZ.ai · observed Aug 28, 2026zai-org/GLM-5.2 README.md at b4734de4facfZ.ai · observed Aug 28, 2026zai-org/GLM-5.2 immutable Hub API metadataZ.ai · observed Aug 28, 2026zai-org/GLM-5.2 tokenizer_config.json at b4734de4facfZ.ai · observed Aug 28, 2026Fireworks Ai catalogFireworks Ai · observed Oct 19, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026Together Ai catalogTogether Ai · observed Oct 19, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
GLM 5.2Z.ai | vs | GLM 5.3Z.ai | family variantstext |
GLM 5.2Z.ai | vs | cross-developer peerstext | |
GLM 5.2Z.ai | vs |  DeepSeek V4 Flash BaseDeepSeek | cross-developer peerstext |
GLM 5.2Z.ai | vs | DeepSeek V4 ProDeepSeek | cross-developer peerstext |
GLM 5.2Z.ai | vs | DeepSeek V4 Pro BaseDeepSeek | cross-developer peerstext |
GLM 5.2Z.ai | vs | GLM 5.3 FlashZ.ai | family variantstext |
GLM 5.2Z.ai | vs | DeepSeek V3.2DeepSeek | cross-developer peerstext |
GLM 5.2Z.ai | vs | DeepSeek V4 FlashDeepSeek | cross-developer peerstext |
GLM 5.2Z.ai | vs | DeepSeek V4 Pro 0813DeepSeek | cross-developer peerstext |
GLM 5.2Z.ai | vs |  Kimi K2 ThinkingMoonshot AI | cross-developer peerstext |
GLM 5.2Z.ai | vs | GLM 5Z.ai | family variantstext |
GLM 5.2Z.ai | vs | GLM 5.1Z.ai | family variantstext |
Questions
GLM 5.2 FAQs
What is GLM 5.2?+
GLM-5.2 is an open-weight language model published by Z.ai. It is developed by Z.ai and its current sourced lifecycle status is active.
What inputs and outputs does GLM 5.2 support?+
GLM 5.2's current record lists Text as input and Text as output.
How much context does GLM 5.2 support?+
The current record lists a 1,049K-token context window and does not report a maximum output length.
Is GLM 5.2 available through an API?+
GLM 5.2 is marked as API-available. The directly sourced provider records currently include Deepinfra, Fireworks Ai, Hugging Face, Openrouter, and Together Ai.
How large is GLM 5.2?+
The current record lists 753.3B total parameters and an unknown active parameter count. Its architecture is GlmMoeDsaForCausalLM.
What capabilities and tasks does GLM 5.2 support?+
GLM 5.2's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are text.
How much does GLM 5.2 cost through an API?+
The lowest directly sourced prices currently attached to GLM 5.2 are $0.75 per million input tokens through Deepinfra and $2.40 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Can GLM 5.2 be self-hosted?+
GLM 5.2 is an open-weight model. Self-hosting is supported, and the recorded license is mit.
Does GLM 5.2 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are zai-org/GLM-5.2.
Which models can GLM 5.2 be compared with?+
The current compatible peer set includes GLM 5.3, NVIDIA Nemotron 3 Ultra 550B A55B BF16, DeepSeek V4 Flash Base, DeepSeek V4 Pro, and DeepSeek V4 Pro Base. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →