GLM-5
by Vultr · family glm · listed Feb 2026RTW
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
Current rates USD per 1M tokens
Input$0.40
Output$1.75
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
glm-5.x-menthol- Context window
- 203K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-02-12
- Last updated
- 2026-02-12
← All Vultr listings