GLM 5
z-ai/glm-5- Z.ai
- Family · GLM 5
- Released 11 Feb 2026
- Open weights
- Text → Text
- Tools · JSON
Spec & list price
Context200K
Max output128K
Input / 1M$1.00
Output / 1M$3.203.2× input
Scores · standing
Intelligence27.9#76/489
Usage
Tokens / day5.0B▼ 3.1% 7d
Usage rank#118
Requests / day216.1K
Tool calls / req0.13
Per request · 30 days
Avg input17.3K1.2× median
Avg output9771.4× median
Cache hit71%about median
Reasoning share44%0.8× median
Tool-call failures1.2%0.6× median
Consumption
Peak 12.1B 8 OctLow 4.1B 31 OctRank today #118
News & trends
21 mentions this week ▲ 75%this model · videos, posts, articles · 30 days
Trending · 14 days
- AI OFM FULL COURSE #5 — PHONE FARM AUTOMATION With GLM 5.352.7K views
- 👀 GLM 5.5 Flash is coming soon?401 upvotes
- DeepSeek 4.1 Flash e GLM 5.3 AGORA É GRÁTIS. Qual a Pegadinha?24.7K views
- GLM 5.1 ranked between GLM 5.3 and GLM 5. Where would you rank Gemini 3 Flash Preview?13 upvotes
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 9 providers, latest day
Output speed#201/33356 tok/s1.2× slower than median
Fastest provider111 tok/sbest of 9 providers
First token#2301.6 s1.6× longer than median
#12 cheapest of 22 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
- 1.7M · 2.1K
Request parameters 17
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
+7 more
- stop
- seed
- frequency_penalty
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Agents with tool calling
- Instruction-following automation
- Terminal-style coding tasks
- Self-hosted general assistants
Think twice for
- Image input
- Very long documents
- Hardest reasoning tasks
Research papers
- Agentic Interpretation: Harness-Governed Evidence Construction for Software Agents15 Oct
- Harness^2: Recursive Agent Harnessing for an Open World9 Oct
- LatentIndex: Cross-Layer Sharing with Layer-Specific Selection for Sparse Attention3 Oct
- Continuous Context Management28 Sep
- Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents1 Sep
- Can Open-Weight Models Compete on Financial Text Comprehension?9 Aug
- Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility29 Jul
- AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?3 Jul
Same family
GLM 5- 44.8
- 33.7
- 26.1
Alternatives
other vendors · similar capability- 26.3
- T25.0
- T25.7
- 29.7
Using GLM 5 at volume?
Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.











