Mistral Nemo
mistralai/mistral-nemoA 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
$0.019Input, per million tokens
$0.030Output, per million tokens
131KContext window
16KLongest answer
131K tokens of context — about 98,304 words, on a scale that ends at 2M.
What it can do
- Tool use
- Open weights
- Takes text
- Gives text
Released 19 Jul 2024 · checked 3 Oct 2026.
On these boards
More from Mistral
- Mistral Medium 3.5$1.50 in
- Mistral Medium 3.5 (batch)$0.75 in
- Mistral Small 4$0.15 in
- Mistral Small 4 (batch)$0.075 in
- Devstral 2 2512$0.40 in
- Ministral 3 14B 2512$0.20 in
- Ministral 3 3B 2512$0.10 in
- Ministral 3 8B 2512$0.15 in
- Ministral 3 8B 2512 (batch)$0.075 in
- Mistral Large 3 2512$0.50 in
- Mistral Large 3 2512 (batch)$0.25 in
- Voxtral Small 24B 2507$0.10 in
- Mistral Medium 3.1$0.40 in
- Mistral Medium 3.1 (batch)$0.20 in
- Codestral 2508$0.30 in
- Codestral 2508 (batch)$0.15 in
- Mistral Small 3.2 24B$0.094 in
- Mistral Medium 3$0.40 in