Macaron V1 Venti
by Novita AI · listed Jul 2026RTW
GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI
Current rates USD per 1M tokens
Input$0.825
Output$2.48
Cache read$0.165
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
mindai/macaron-v1-venti- Context window
- 1.0M tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-07-21
- Last updated
- 2026-07-21
← All Novita AI listings