Zhipu AI model product
GLM 5
GLM-5 is Zhipu AI's flagship foundation model designed for complex system engineering and long-range Agent tasks, shifting focus from coding to engineering.
Updated Aug 12, 2026. Default version: GLM-5
LLMBoard score67.2GLM-5
Coverage20%5 benchmark families
Context window204.8KTokens
Official input price$1Zhipu AI API
GLM 5 Specifications
Technical details for the model's default version.
- Version
- GLM-5
- Released
- Feb 11, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 744B
- Context window
- 204.8K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 5 Benchmark Results
Benchmark scores for GLM-5.
| t2-bench | 89.7% | 03 | 23 | 90.9% | C | |
| MCP Atlas | 67.8% | 21 | 31 | 33.3% | C | |
| SWE-Bench Verified | 77.8% | 22 | 105 | 79.8% | C | |
| BrowseComp | 75.9% | 25 | 58 | 57.9% | C | |
| Terminal-Bench 2.0 | 56.2% | 28 | 49 | 43.8% | C |
GLM 5 Arena Results
Preference and agent-evaluation results for the default version.
| text | overall | 48 | 1445.3 | 27,887 | N/A | |
| webdev | overall | 50 | 1435.7 | 7,061 | N/A | |
| text factuality | overall | 51 | 1451.1 | 27,661 | N/A | |
| text style control | overall | 51 | 1456.9 | 27,887 | N/A |
GLM 5 Runtime Performance
Provider-specific output speed and catalog latency for GLM-5. Runtime does not affect the capability score.
| ZAI | 30 tok/s | 3 s | 200K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1 input, $3.2 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.48 input, $1.9 output per 1M via CrofAI
- Tracked offerings
- 41
| Alibaba Coding Plan (China) | glm-5 | global | N/A | N/A | 202.8K | |
| Alibaba Coding Plan | glm-5 | global | N/A | N/A | 202.8K | |
| Alibaba Token Plan | glm-5 | global | N/A | N/A | 202.8K | |
| Tencent Coding Plan (China) | glm-5 | global | N/A | N/A | 202.8K | |
| Alibaba Token Plan (China) | glm-5 | global | N/A | N/A | 202.8K | |
| CrofAI | glm-5 | global | $0.48 | $1.9 | 202.8K | |
| NanoGPT | zai-org/glm-5 | global | $0.50 | $2.55 | 200K | |
| ZenMux | z-ai/glm-5 | global | $0.58 | $2.6 | 200K | |
| CrossModel | z-ai/glm-5 | global | $0.60 | $3 | 200K | |
| 302.AI | glm-5 | global | $0.60 | $2.6 | 204.8K | |
| GMI Cloud | zai-org/GLM-5-FP8 | global | $0.60 | $1.92 | 202.8K | |
| Deep Infra | zai-org/GLM-5 | global | $0.60 | $2.08 | 202.8K | |
| LLM Gateway | glm-5 | global | $0.72 | $2.3 | 203K | |
| DInference | glm-5 | global | $0.75 | $2.4 | 200K | |
| DigitalOcean | glm-5 | global | $0.75 | $2.4 | 64K | |
| Meganova | zai-org/GLM-5 | global | $0.80 | $2.56 | 202.8K | |
| Alibaba (China) | glm-5 | global | $0.86 | $3.15 | 202.8K | |
| Baseten | zai-org/GLM-5 | global | $0.95 | $3.15 | 202.8K | |
| FastRouter | z-ai/glm-5 | global | $0.95 | $3.15 | 204.8K | |
| OpenRouter | z-ai/glm-5 | global | $0.95 | $2.55 | 204.8K | |
| Cortecs | glm-5 | global | $0.988 | $3.16 | 202.8K | |
| Zhipu AI | glm-5 | global | $1 | $3.2 | 204.8K | |
| Impossibl | zai/glm-5 | global | $1 | $3.2 | 204.8K | |
| OpenCode Go | glm-5 | global | $1 | $3.2 | 202.8K | |
| Poe | novita/glm-5 | global | $1 | $3.2 | 205K | |
| Nebius Token Factory | zai-org/GLM-5 | global | $1 | $3.2 | 200K | |
| OpenCode Zen | glm-5 | global | $1 | $3.2 | 204.8K | |
| Abacus | zai-org/GLM-5 | global | $1 | $3.2 | 204.8K | |
| Venice AI | zai-org-glm-5 | global | $1 | $3.2 | 198K | |
| Together AI | zai-org/GLM-5 | global | $1 | $3.2 | 202.8K | |
| Ofox | z-ai/glm-5 | global | $1 | $3.2 | 204.8K | |
| OrcaRouter | z-ai/glm-5 | global | $1 | $3.2 | 204.8K | |
| Vertex | zai-org/glm-5-maas | global | $1 | $3.2 | 202.8K | |
| Amazon Bedrock | zai.glm-5 | global | $1 | $3.2 | 202.8K | |
| TensorX | z-ai/glm-5 | global | $1 | $3.2 | 202.8K | |
| Kilo Gateway | z-ai/glm-5 | global | $1 | $3.2 | 204.8K | |
| Merge Gateway | zai/glm-5 | global | $1 | $3.2 | 200K | |
| Vercel AI Gateway | zai/glm-5 | global | $1 | $3.2 | 202.8K | |
| NovitaAI | zai-org/glm-5 | global | $1 | $3.2 | 202.8K | |
| Hugging Face | zai-org/GLM-5 | global | $1 | $3.2 | 202.8K | |
| Z.AI | glm-5 | global | $1 | $3.2 | 204.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GLM 5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GLM-5 | 67.2 | 744B | 204.8K | 131.1K | Yes | MIT |
What is GLM 5?
Key information about GLM 5 and its available data.
GLM-5 is Zhipu AI's flagship foundation model designed for complex system engineering and long-range Agent tasks, shifting focus from coding to engineering. 5T tokens. GLM-5 integrates DeepSeek Sparse Attention for higher token efficiency while preserving long-context quality.
It supports 200K context length and 128K max output tokens, with capabilities including thinking modes, real-time streaming, function calling, context caching, and structured output. 5 in code-logic density and systems-engineering capability.
Data as of 2026-08-11.
GLM 5 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GLM 5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5.1
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 5.2
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 4.5
Zhipu AI
FAQ
Common questions about GLM 5.
When was GLM 5 released?
GLM 5's default version was released on Feb 11, 2026.
How much does GLM 5 cost?
GLM 5's official API price is $1 per million input tokens and $3.2 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.48 input and $1.9 output via CrofAI.
Who created GLM 5?
GLM 5 was created by Zhipu AI.
What is the context window for GLM 5?
The default version has a 204.8K token context window.
Is GLM 5 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 5?
41 provider offerings are linked to the default version.
What models should I compare GLM 5 with?
Nearby ranked alternatives include Grok 4 Heavy, Qwen3.6 Plus, Gemini 3 Pro.