GLM 4.6V
z-ai/glm-4.6v- Z.ai
- Family · GLM 4.6V
- Released 8 Dec 2025
- Open weights
- Image · Text · Video → Text
- Tools · Vision
Not on OSMEXO yet
Spec & list price
Context128K
Max output32K
Input / 1M$0.30
Output / 1M$0.903× input
Scores · standing
Intelligence11.2#230/490
Usage
Tokens / day942.3M▲ 78% 7d
Usage rank#197
Requests / day300.6K
Tool calls / req0.03
Per request · 30 days
Avg input2.9K0.2× median
Avg output3380.5× median
Cache hit38%0.5× median
Reasoning share62%about median
Tool-call failures4.9%2.6× median
Consumption
Peak 942.3M 1 NovLow 92.0M 4 OctRank today #197
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 2 providers, latest day
Output speed#303/33425 tok/s2.6× slower than median
First token#2662.56 s2.4× longer than median
#18 cheapest of 34 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Technical details
- Tokenizer
- Other
- License
- MIT
- Parameters
- 108B
- Moderation
- none
- Downloads · likes
- 4.9K · 398
Request parameters 14
- tools
- tool_choice
- response_format
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
- stop
+4 more
- seed
- frequency_penalty
- presence_penalty
- repetition_penalty
Interesting facts
- Less output room than similar models (32.8K against a 65.5K median).
- Weekdays average 191.5M tokens a day against 212.9M on weekends.
When to use
Best for
- Image and video understanding
- Document and screenshot analysis
- Multimodal agents that call tools
- Math reasoning over visual inputs
- Self-hosted vision assistants
Think twice for
- Image generation
- Strict structured-output pipelines
- Hardest terminal-style agent runs
- Audio input
Alternatives
other vendors · similar capability- 11.6
- 13.1
- 6.7
- 15.6
Want GLM 4.6V on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.