GLM 4.7
z-ai/glm-4.7- Z.ai
- Family · GLM 4
- Released 22 Dec 2025
- Open weights
- Text → Text
- Tools · JSON
Spec & list price
Context200K
Max output128K
Input / 1M$0.60
Output / 1M$2.203.7× input
Scores · standing
Intelligence22.2#120/489
Coding45.3#78/196
Usage
Tokens / day4.4B▼ 4.9% 7d
Usage rank#118
Requests / day241.7K
Tool calls / req0.03
Per request · 30 days
Avg input11.5K0.8× median
Avg output5370.8× median
Cache hit57%0.8× median
Reasoning share40%0.7× median
Tool-call failures2.7%1.4× median
Consumption
Peak 8.6B 7 OctLow 2.6B 1 NovRank today #118
News & trends
2 mentions this weekthis model · videos, posts, articles · 30 days
Trending · 14 days
- DeepSeek 4.1 is the second model to be ranked in Bad. Where would you rank GLM 4.7?21 upvotes
- Stuck between GLM 4.7, 4.6, and Kimi K2.5. Also, which provider should I use between OpenRouter and DeepInfra?49 upvotes
News · latest from Z.ai
- 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
- ReplaySSM: Rethinking State Storage for Faster Hybrid-Model DecodingNVIDIA · 12 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 6 providers, latest day
Output speed#306/33426 tok/s2.5× slower than median
Fastest provider28 tok/sbest of 6 providers
First token#2602.0 s1.9× longer than median
#18 cheapest of 31 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases22.2
Technical details
- Tokenizer
- Other
- License
- MIT
- Parameters
- 358B
- Moderation
- none
- Downloads · likes
- 72.3K · 2.1K
Request parameters 18
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+8 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- presence_penalty
- repetition_penalty
- top_a
Interesting facts
- The most used of 3 GLM 4 models by tokens last month.
- Released 315 days ago, the newest of 3 GLM 4 models.
When to use
Best for
- Code generation and debugging
- Math and reasoning problems
- Agent workflows with tool calling
- Self-hosted general assistants
Think twice for
- Image input
- Very long documents
- Newest-generation agent work
Research papers
- MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory6 Oct
- A Hub of Short Rows Inflates Intrinsic Dimension Estimation of Token Embeddings30 Aug
- SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning14 Aug
- Can Open-Weight Models Compete on Financial Text Comprehension?9 Aug
- Can Agentic Trading Systems Pay for Their Own Intelligence?11 Jul
- Reinforcement learning to improve large language model-based automated code compliance systems21 Jun
- Uncertainty Decomposition for Clarification Seeking in LLM Agents17 Jun
- Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries8 Jun
Same family
GLM 4- 18.5
- 12.8
Alternatives
other vendors · similar capability- 26.3
- 21.8
- T25.0
- 21.5
Using GLM 4.7 at volume?
Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.