LLM ReferenceLLM Reference

Mistral NeMo

MistralAIOpen Source
2 models2024Up to 128K ctxFrom $0.02/1M input

About

Mistral AI and NVIDIA collaborative family built around the 12B Mistral NeMo long-context open-weight model line.

Specifications(2 models)

Mistral NeMo model specifications comparison
ModelReleasedContextParameters
Mistral NeMo Instruct (2407)2024-07128K12B
Mistral NeMo (2407)2024-07128K12B

Available From(11 providers)

Pricing

Mistral NeMo model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Mistral NeMo (2407)OpenRouter$0.02$0.04Serverless
Mistral NeMo Instruct (2407)Novita AI$0.08$0.24Serverless
Mistral NeMo (2407)Mistral AI Studio$0.15$0.15Serverless
Mistral NeMo Instruct (2407)Arcee AI$0.15$0.45Serverless
Mistral NeMo (2407)Bitdeer AI$0.18$0.54Serverless
Mistral NeMo (2407)Fireworks AI$0.2$0.2Serverless
Mistral NeMo Instruct (2407)Microsoft Foundry$0.3$0.3Provisioned
Mistral NeMo (2407)SiliconFlow$0.3$0.3Serverless
Mistral NeMo Instruct (2407)Replicate API$0.45$0.45Serverless
Mistral NeMo Instruct (2407)Fireworks AI$0.9$0.9Serverless
Mistral NeMo Instruct (2407)DeepInfra$2$4Serverless

Frequently Asked Questions

What is Mistral NeMo?
Mistral AI and NVIDIA collaborative family built around the 12B Mistral NeMo long-context open-weight model line.
How many models are in the Mistral NeMo family?
The Mistral NeMo family contains 2 models.
What is the latest Mistral NeMo model?
The latest model is Mistral NeMo Instruct (2407), released in 2024-07.
How much does Mistral NeMo cost?
Mistral NeMo models range from $0.02/1M to $2/1M input tokens depending on the model and provider.

Models(2)