mistralai/mistral-nemoMistral Nemo is a 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. Released July 19, 2024. Knowledge cutoff April 30, 2024. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license. Pricing: $0.02/M input, $0.03/M output.