Mistral Nemo
by NanoGPT · family mistral-nemo · listed Jan 2024W
12B parameter model with multilingual support.
Current rates USD per 1M tokens
Input$0.10
Output$0.121
Cache read$0.0502
Cache write—
Against the market
On the record
- Model id
mistralai/mistral-nemo-instruct-2407- Context window
- 16K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2024-01-01
- Last updated
- 2024-01-01
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Pioneer$0.02 in · $0.03 out
- Meganova$0.02 in · $0.04 out
- IO.NET$0.02 in · $0.04 out
- OVHcloud AI Endpoints$0.14 in · $0.14 out
- Cortecs$0.145 in · $0.145 out
- DigitalOcean$0.30 in · $0.30 out