sarvam-m
by Nvidia · listed Jul 2025TW
Efficient Indian-language reasoning model for chat, coding, and multilingual work
Current rates USD per 1M tokens
Inputfree
Outputfree
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
sarvamai/sarvam-m- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-07-25
- Last updated
- 2025-07-25
← All Nvidia listings