GLM 4.6 Thinking
by NanoGPT · family glm · listed Sep 2025RT
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Current rates USD per 1M tokens
Input$0.40
Output$1.50
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
z-ai/glm-4.6:thinking- Context window
- 200K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-09-29
- Last updated
- 2025-09-29
← All NanoGPT listings