Identity
- Status
- active
- Developer ID
glm-5.3- Released
- Not reported
- Version
- GLM-5.3
- License
- Unknown
Z.aiGLM-5.3
GLM-5.3 is Z.ai's text flagship for software engineering and long-horizon agent tasks, with reasoning always enabled.
- Context
- 1,000,000 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 | $1.20 | $4.00 | $0.12 | — | Sep 2, 2026 | Provider-reported |
Z.aiAvailable | $1.40 | $4.40 | $0.26 | — | Aug 29, 2026 | Provider-reported |
Benchmarks
All benchmark results →| GLM-5.3Z.ai | LiveBench2026-06-25 | 79.15 | 62,090 | 1,270 | glm-5.3average per case | Recomputedwinner eligible | Third-party benchmark |
| GLM-5.3Z.ai | LMArena Agent Arenaagent-2026-08-31-011508720696 | 3.82 | — | 41,022 | GLM 5.3 (Max); 95% CI [3.01733683, 4.62585790]; sessions 41022; observations 2958163; rank 20unknown | Original sourcewinner eligible | Third-party benchmark |
| GLM-5.3Z.ai | LMArena Text Arenatext-2026-09-01-011508720696 | 1,474.49 | — | 7,401 | glm-5.3-max; 95% CI [1467.12172899, 1481.86064533]; votes 7401; rank 18unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Context
- 1,000,000 tokens
- Maximum output
- 131,072 tokens
- Total parameters
- Unknown
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- agents, chat, reasoning, structured outputs, tools
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesglm-5.3, glm-5.3-max
Explicit Unknowns
- Release date
- Architecture
- Tokenizer
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
GLM-5.3Z.ai | vs |  Hy4 previewTencent | cross-developer peerstext |
GLM-5.3Z.ai | vs |  Qwen3.7-PlusQwen | cross-developer peerstext |
GLM-5.3Z.ai | vs | GLM-5.3-FlashZ.ai | family variantstext |
GLM-5.3Z.ai | vs | GLM-5.2Z.ai | family variantstext |
GLM-5.3Z.ai | vs | GLM-5Z.ai | family variantstext |
GLM-5.3Z.ai | vs | GLM-5.1Z.ai | family variantstext |
GLM-5.3Z.ai | vs |  ERNIE 5.1Baidu | cross-developer peerstext |
GLM-5.3Z.ai | vs | ERNIE X1.1Baidu | cross-developer peerstext |
GLM-5.3Z.ai | vs |  Sonar Deep ResearchPerplexity | cross-developer peerstext |
GLM-5.3Z.ai | vs | Sonar Reasoning ProPerplexity | cross-developer peerstext |
GLM-5.3Z.ai | vs |  Command ACohere | cross-developer peerstext |
GLM-5.3Z.ai | vs |  Gemini 2.5 Flash-LiteGoogle DeepMind | cross-developer peerstext |
Questions
GLM-5.3 FAQs
What is GLM-5.3?+
GLM-5.3 is Z.ai's text flagship for software engineering and long-horizon agent tasks, with reasoning always enabled. It is developed by Z.ai and its current sourced lifecycle status is active.
What inputs and outputs does GLM-5.3 support?+
GLM-5.3's current record lists Text as input and Text as output.
How much context does GLM-5.3 support?+
The current record lists a 1,000,000-token context window and a maximum output of 131,072 tokens.
Is GLM-5.3 available through an API?+
GLM-5.3 is marked as API-available. The directly sourced provider records currently include Deepinfra and Z.ai.
How much does GLM-5.3 cost through an API?+
The lowest directly sourced prices currently attached to GLM-5.3 are $1.20 per million input tokens through Deepinfra and $4.00 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
What capabilities and tasks does GLM-5.3 support?+
GLM-5.3's recorded capabilities are agents, chat, reasoning, structured outputs, and tools. Its supported tasks are coding, reasoning, and text.
Can GLM-5.3 be self-hosted?+
GLM-5.3 is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
Does GLM-5.3 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are glm-5.3 and glm-5.3-max.
Which models can GLM-5.3 be compared with?+
The current compatible peer set includes Hy4 preview, Qwen3.7-Plus, GLM-5.3-Flash, GLM-5.2, and GLM-5. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for GLM-5.3?+
GLM-5.3 was last verified Aug 29, 2026 from Z.ai's primary source, “GLM-5.3 | Z.AI Developer Document.” The evidence is classified as official fact.