GLM 5.1
z-ai/glm-5.1- Z.ai
- Family · GLM 5
- Released 7 Apr 2026
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context200K
Max output128K
Input / 1M$1.40
Output / 1M$4.403.1× input
Scores · standing
Intelligence26.1#86/489
Coding55.8#56/196
Usage
Tokens / day2.6B▼ 2.1% 7d
Usage rank#149
Requests / day143.3K
Tool calls / req0.11
Per request · 30 days
Avg input11.9K0.8× median
Avg output1.2K1.7× median
Cache hit69%about median
Reasoning share68%1.2× median
Tool-call failures2.6%1.4× median
Consumption
Peak 5.9B 28 OctLow 1.9B 31 OctRank today #149
News & trends
133 mentions this week ▲ 233%GLM 5 family · videos, posts, articles · 30 days
Trending · 14 days · GLM 5 family
- GLM 5.3 can autonomously compromise recent versions of Mozilla Firefox608 upvotes
- @EpochAIResearch on X82.3K views
- Hermes and REA and GLM 5.3 = Reverse engineering TikTok app for less than $2019 points
- 👀 GLM 5.5 Flash is coming soon?401 upvotes
- Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)178 points
- Запуск ИИ модели GLM 5.2 без видеокарты на ноутбуке238.3K views
- Project Maya Deepseek V4.1 Flash 1017 + GLM 5.3 Local Ai Review58.2K views
News · latest from GLM 5
- Hermes and REA and GLM 5.3 = Reverse engineering TikTok app for less than $20scraping.club · 29 Oct
- GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behaviorlesswrong.com · 27 Oct
- Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)blog.cloudflare.com · 26 Oct
- Together Link: open models in the harness you already use. Start with one command today.Together AI · 5 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 13 providers, latest day
Output speed#187/33359 tok/s1.1× slower than median
Fastest provider129 tok/sbest of 13 providers
First token#1861.22 s1.2× longer than median
#20 cheapest of 24 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases44.8
Technical details
- Tokenizer
- Other
- License
- MIT
- Parameters
- 754B
- Moderation
- none
- Downloads · likes
- 1.0M · 1.9K
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Agents with heavy tool calling
- Instruction-following automation
- Coding and terminal tasks
- Self-hosted general assistants
Think twice for
- Image input
- Very long documents
- Hardest science questions
Research papers
- Detecting Insecure Compositions of Clean Agent Skills via Capability-Flow Graph Analysis23 Oct
- HyScale: Scaling Long-Context Training for Learned Sparse Attention23 Oct
- Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms22 Sep
- ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search11 Sep
- T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks10 Sep
- PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents27 Aug
- Not a Monolith: Lab-Level Divergence in the Cooperative Equilibria of Chinese Frontier LLM Agents10 Aug
- Who Verifies the Benchmark? Decentralizing Trust in Large Language Model Evaluation7 Aug
Same family
GLM 5- 44.8
- 33.7
- 27.9
Alternatives
other vendors · similar capability- T25.0
- 30.1
- 29.7
- 24.1
Want GLM 5.1 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.