Ling 3.0 Tiny
by NanoGPT · family ling · listed Aug 2026TW
Lightweight hybrid-linear MoE reasoning model with 7.9B total and 1.3B active parameters for on-device deployment and offline agents
Current rates USD per 1M tokens
Input$0.015
Output$0.045
Cache read$0.003
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
inclusionai/ling-3.0-tiny- Context window
- 262K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-07
- Last updated
- 2026-08-07
← All NanoGPT listings