GLM-5 Turbo
z-ai/glm-5-turbo- Z.ai
- Family · GLM-5 Turbo
- Released 15 Mar 2026
- Text → Text
- Tools
Not on OSMEXO yet
Spec & list price
Context198K
Max output128K
Input / 1M$1.20
Output / 1M$4.003.3× input
Scores · standing
Intelligence26.6#81/490
Usage
Tokens / day423.3M▲ 30% 7d
Usage rank#235
Requests / day20.3K
Tool calls / req0.16
Per request · 30 days
Avg input16.3Kabout median
Avg output638about median
Cache hit80%1.1× median
Reasoning share43%0.8× median
Tool-call failures2.9%1.6× median
Consumption
Peak 555.5M 24 OctLow 140.5M 18 OctRank today #235
News & trends
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 providers, latest day
Output speed#293/33427 tok/s2.3× slower than median
First token#3074.23 s3.9× longer than median
#18 cheapest of 24 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Technical details
- Tokenizer
- Other
- Moderation
- none
Request parameters 9
- tools
- tool_choice
- response_format
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
When to use
Best for
- Fast agents that call tools
- Instruction-following assistants
- Long document reasoning
- Science question answering
Think twice for
- Image understanding
- Strict structured-output pipelines
- Self-hosting (weights not confirmed open)
- Hardest research-level reasoning
Research papers
- Citation Discipline in Spec-Driven Development: A Cross-Model Empirical Study of Output Determinism and Automated Hallucination Detection in LLM-Generated Code28 Jun
- Bigger Isn't Always Better: A Comparative Evaluation of LLMs for Automated Code Review9 Apr
- SKILLS: Structured Knowledge Injection for LLM-Driven Telecommunications Operations16 Mar
Alternatives
other vendors · similar capability- 26.3
- T25.0
- 30.1
- 29.7
Want GLM-5 Turbo on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.