Mistral NeMo 12B
Mistral's Apache-licensed 12B model built with NVIDIA — strong multilingual quality for its size.
Pricing
InputOpen weights / $0.15 / 1M hosted
OutputOpen weights / $0.15 / 1M hosted
Cost bandFree/open
Free tierOpen weights (Apache 2.0); hosted pricing via Mistral API.
Limits
Context window128k checked Jul 19, 2026
Max outputRuntime-dependent
Knowledge cutoffQ2 2024
DeploymentSelf-hosted, Mistral La Plateforme, Hugging Face
OpenAI-compatible APIYes
ModalitiesText
Where it fits
Best forSelf-hosted general use, multilingual workloads, and teams needing a permissive open model.
Business fitGood default open model for European compliance-conscious deployments.
Capabilities
Open weights (Apache 2.0)MultilingualFunction calling
Benchmark scores
Composite60 / 100
Coding58 / 100 (HumanEval)
Reasoning60 / 100 (MMLU-Pro)
Long context55 / 100
Instruction following64 / 100 (MT-Bench)
Editorial aggregate of published benchmark results as of Sep 1, 2024. These are not independent measurements run by this site.
Change history
No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/mistralai/mistral-nemo
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.