Mistral NeMo Models by MistralAI
2 models2024Up to 128k ctxFrom $0.02/1M input
Details
ResearcherMistralAI
LicenseApache 2.0(OSI)
Commercial useCommercial use allowed
Models2
Released2024
Max context128k
About
Mistral AI and NVIDIA collaborative family built around the 12B Mistral NeMo long-context open-weight model line.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
2 in view
Mistral NeMo Instruct (2407)Current
Use when the workload needs 128k context and 12B parameters.
2024-07128k context12B parameters
Mistral NeMo (2407)Current
Use when the workload needs 128k context and 12B parameters.
2024-07128k context12B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral NeMo Instruct (2407) | Use when the workload needs 128k context and 12B parameters. | 2024-07 | 128k context12B parameters | Current |
| Mistral NeMo (2407) | Use when the workload needs 128k context and 12B parameters. | 2024-07 | 128k context12B parameters | Current |
Release Timeline
1 release group2024-07
2 current
Mistral NeMo (2407)
Current128k context12B parameters
Mistral NeMo Instruct (2407)
Current128k context12B parameters
Specifications(2 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Mistral NeMo Instruct (2407) | 2024-07 | 128k | 12B |
| Mistral NeMo (2407) | 2024-07 | 128k | 12B |
Available From(12 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Mistral NeMo Instruct (2407) | DeepInfra | $0.02 | $0.04 | Serverless |
| Mistral NeMo (2407) | OpenRouter | $0.02 | $0.03 | Serverless |
| Mistral NeMo (2407) | Vercel AI Gateway | $0.02 | $0.04 | Serverless |
| Mistral NeMo (2407) | Novita AI | $0.04 | $0.17 | Serverless |
| Mistral NeMo Instruct (2407) | Novita AI | $0.08 | $0.24 | Serverless |
| Mistral NeMo (2407) | Mistral AI Studio | $0.15 | $0.15 | Serverless |
| Mistral NeMo Instruct (2407) | Arcee AI | $0.15 | $0.45 | Serverless |
| Mistral NeMo (2407) | Bitdeer AI | $0.18 | $0.54 | Serverless |
| Mistral NeMo (2407) | Fireworks AI | $0.2 | $0.2 | Serverless |
| Mistral NeMo Instruct (2407) | Microsoft Foundry | $0.3 | $0.3 | Provisioned |
| Mistral NeMo (2407) | SiliconFlow | $0.3 | $0.3 | Serverless |
| Mistral NeMo Instruct (2407) | Replicate API | $0.45 | $0.45 | Serverless |
| Mistral NeMo Instruct (2407) | Fireworks AI | $0.9 | $0.9 | Serverless |
Frequently Asked Questions
- What is Mistral NeMo used for?
- Mistral AI and NVIDIA collaborative family built around the 12B Mistral NeMo long-context open-weight model line.
- How does Mistral NeMo compare to Ministral?
- Mistral NeMo by MistralAI is strongest where you need its listed use cases, while Ministral by MistralAI is the closest related family to check for vision and multimodal work. Mistral NeMo has 2 listed variants and reaches up to 128k context, while Ministral reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
- Which Mistral NeMo model should I use?
- For the lowest listed input price, start with Mistral NeMo Instruct (2407) through DeepInfra at $0.02/1M input tokens. For the most capable/latest local choice, evaluate Mistral NeMo Instruct (2407) with 128k context.
