Zhipu AI model product
GLM 5.1
AI's next-generation flagship foundation model designed for long-horizon agentic engineering tasks.
Updated Aug 12, 2026. Default version: GLM-5.1
LLMBoard score69.6GLM-5.1
Coverage80%18 benchmark families
Context window200KTokens
Official input price$1.4Zhipu AI API
GLM 5.1 Specifications
Technical details for the model's default version.
- Version
- GLM-5.1
- Released
- Apr 7, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 754B
- Context window
- 200K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 5.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 5.1 Benchmark Results
Benchmark scores for GLM-5.1.
| Vending-Bench 2 | 5,634.41 usd | 02 | 4 | 66.7% | C | |
| AIME 2026 | 95.3% | 03 | 18 | 88.2% | C | |
| TAU3-Bench | 70.6% | 03 | 5 | 50.0% | C | |
| NL2Repo | 42.7% | 08 | 14 | 46.1% | C | |
| CyberGym | 68.7% | 09 | 11 | 20.0% | C | |
| HMMT 2025 | 94.0% | 10 | 33 | 71.9% | C | |
| IMO-AnswerBench | 83.8% | 10 | 19 | 50.0% | C | |
| FrontierSWE | 31.0% | 11 | 15 | 28.6% | B | |
| HMMT Feb 26 | 82.6% | 11 | 11 | 0.0% | C | |
| Terminal-Bench 2.0 | 69.0% | 11 | 49 | 79.2% | C | |
| Finance Agent v2 | 44.8% | 12 | 26 | 56.0% | B | |
| Humanity's Last Exam | 52.3% | 15 | 93 | 84.8% | C | |
| MCP Atlas | 71.8% | 18 | 31 | 43.3% | C | |
| SWE-Bench Pro | 58.4% | 18 | 45 | 61.4% | C | |
| BrowseComp | 79.3% | 21 | 58 | 64.9% | C | |
| Toolathlon | 40.7% | 24 | 31 | 23.3% | C | |
| LiveBench | 70.2% | 29 | 38 | 24.3% | B | |
| GPQA | 86.2% | 46 | 234 | 80.7% | C |
GLM 5.1 Arena Results
Preference and agent-evaluation results for the default version.
| agent steerability | overall | 22 | 0.0 | N/A | 53.6K | |
| agent task outcome explicit | overall | 23 | 0.0 | N/A | 43K | |
| agent | overall | 24 | 0.0 | N/A | 3.1M | |
| agent praise complaint | overall | 25 | 0.0 | N/A | 14.5K | |
| webdev | overall | 26 | 1511.5 | 8,533 | N/A | |
| text | overall | 27 | 1463.8 | 38,626 | N/A | |
| agent bash recovery steps | overall | 32 | -0.0 | N/A | 110.4K | |
| text factuality | overall | 37 | 1457.6 | 38,477 | N/A | |
| text style control | overall | 38 | 1467.4 | 38,626 | N/A | |
| agent tool hallucination | overall | 39 | -0.0 | N/A | 2.9M |
GLM 5.1 Runtime Performance
Provider-specific output speed and catalog latency for GLM-5.1. Runtime does not affect the capability score.
| FriendliAI | 354.951 tok/s | 1.583 s | 200K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 5.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.4 input, $4.4 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.45 input, $2.15 output per 1M via CrofAI
- Tracked offerings
- 50
| Zhipu AI Coding Plan | glm-5.1 | global | N/A | N/A | 200K | |
| Kenari | glm-5-1 | global | N/A | N/A | 200K | |
| Alibaba Token Plan | glm-5.1 | global | N/A | N/A | 202.8K | |
| Umans AI Coding Plan | umans-glm-5.1 | global | N/A | N/A | 204.8K | |
| Alibaba Token Plan (China) | glm-5.1 | global | N/A | N/A | 202.8K | |
| CrofAI | glm-5.1 | global | $0.45 | $2.15 | 202.8K | |
| HPC-AI | zai-org/glm-5.1 | global | $0.615 | $2.46 | 202K | |
| NanoGPT | zai-org/glm-5.1 | global | $0.75 | $2.6 | 200K | |
| EmpirioLabs AI | glm-5-1 | global | $0.825 | $3.3 | 202K | |
| EBCloud | GLM-5.1 | global | $0.8571 | $3.43 | 200K | |
| 302.AI | glm-5.1 | global | $0.86 | $3.5 | 200K | |
| Alibaba (China) | glm-5.1 | global | $0.87 | $3.48 | 202.8K | |
| ZenMux | z-ai/glm-5.1 | global | $0.8781 | $3.51 | 200K | |
| LLM Gateway | glm-5.1 | global | $0.931 | $2.93 | 204.8K | |
| DigitalOcean | glm-5.1 | global | $0.975 | $4.3 | 163.8K | |
| Pioneer | zai-org/GLM-5.1 | global | $0.98 | $3.08 | 202.8K | |
| GMI Cloud | zai-org/GLM-5.1-FP8 | global | $0.98 | $3.08 | 202.8K | |
| CrossModel | z-ai/glm-5.1 | global | $1 | $3.8 | 200K | |
| Wafer | GLM-5.1 | global | $1 | $3.2 | 202.8K | |
| Hugging Face | zai-org/GLM-5.1 | global | $1 | $3.2 | 202.8K | |
| FastRouter | z-ai/glm-5.1 | global | $1.05 | $3.5 | 200K | |
| Deep Infra | zai-org/GLM-5.1 | global | $1.05 | $3.5 | 202.8K | |
| DInference | glm-5.1 | global | $1.25 | $3.89 | 200K | |
| Baseten | zai-org/GLM-5.1 | global | $1.3 | $4.3 | 202.8K | |
| Kilo Gateway | z-ai/glm-5.1 | global | $1.38 | $4.4 | 202.8K | |
| NovitaAI | zai-org/glm-5.1 | global | $1.38 | $4.4 | 204.8K | |
| Cortecs | glm-5.1 | global | $1.38 | $4.35 | 202.8K | |
| Zhipu AI | glm-5.1 | global | $1.4 | $4.4 | 200K | |
| Impossibl | zai/glm-5.1 | global | $1.4 | $4.4 | 200K | |
| Weights & Biases | zai-org/GLM-5.1 | global | $1.4 | $4.4 | 202.8K | |
| OpenCode Go | glm-5.1 | global | $1.4 | $4.4 | 202.8K | |
| Friendli | zai-org/GLM-5.1 | global | $1.4 | $4.4 | 202.8K | |
| OpenCode Zen | glm-5.1 | global | $1.4 | $4.4 | 204.8K | |
| Ambient | zai-org/GLM-5.1-FP8 | global | $1.4 | $4.4 | 202.8K | |
| Abacus | zai-org/GLM-5.1 | global | $1.4 | $4.4 | 204.8K | |
| Inceptron | zai-org/GLM-5.1-FP8 | global | $1.4 | $4.4 | 202.8K | |
| Together AI | zai-org/GLM-5.1 | global | $1.4 | $4.4 | 202.8K | |
| Auriko | glm-5.1 | global | $1.4 | $4.4 | 200K | |
| Umans AI | umans-glm-5.1 | global | $1.4 | $4.4 | 204.8K | |
| Ofox | z-ai/glm-5.1 | global | $1.4 | $4.4 | 200K | |
| OrcaRouter | z-ai/glm-5.1 | global | $1.4 | $4.4 | 200K | |
| TensorX | z-ai/glm-5.1 | global | $1.4 | $4.4 | 202.8K | |
| Merge Gateway | zai/glm-5.1 | global | $1.4 | $4.4 | 200K | |
| Vercel AI Gateway | zai/glm-5.1 | global | $1.4 | $4.4 | 202.8K | |
| OpenRouter | z-ai/glm-5.1 | global | $1.4 | $4.4 | 204.8K | |
| Z.AI | glm-5.1 | global | $1.4 | $4.4 | 200K | |
| Charm Hyper | glm-5.1 | global | $1.52 | $4.79 | 202.8K | |
| Venice AI | zai-org-glm-5-1 | global | $1.54 | $4.84 | 200K | |
| GreenPT | glm-5.1 | global | $1.76 | $5.52 | 200K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GLM 5.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GLM-5.1 | 69.6 | 754B | 200K | 131.1K | Yes | MIT |
What is GLM 5.1?
Key information about GLM 5.1 and its available data.
AI's next-generation flagship foundation model designed for long-horizon agentic engineering tasks.
Built on a 754B MoE architecture (40B active parameters), it can work continuously and autonomously on a single task for up to 8 hours, completing the full loop from planning and execution to iterative optimization and delivery. 4) and demonstrates strong performance across coding, reasoning, and agentic benchmarks.
It supports 200K context length, 128K max output tokens, thinking mode, function calling, structured output, context caching, and MCP integration. 6 with particular strengths in sustained execution and complex engineering optimization.
Data as of 2026-08-11.
GLM 5.1 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GLM 5.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5
Zhipu AI
ZA
GLM 5.2
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 4.5
Zhipu AI
FAQ
Common questions about GLM 5.1.
When was GLM 5.1 released?
GLM 5.1's default version was released on Apr 7, 2026.
How much does GLM 5.1 cost?
GLM 5.1's official API price is $1.4 per million input tokens and $4.4 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.45 input and $2.15 output via CrofAI.
Who created GLM 5.1?
GLM 5.1 was created by Zhipu AI.
What is the context window for GLM 5.1?
The default version has a 200K token context window.
Is GLM 5.1 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 5.1?
50 provider offerings are linked to the default version.
What models should I compare GLM 5.1 with?
Nearby ranked alternatives include GPT-5.2, MiniMax M3, Hy3.