Mercury 3
by NanoGPT · family mercury · listed Oct 2026RT
Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use
Current rates USD per 1M tokens
Input$0.10
Output$0.35
Cache read$0.01
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
inception/mercury-3- Context window
- 1M tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-10-16
- Last updated
- 2026-10-20
← All NanoGPT listings