Mistral Nemo
Model Information
Display Name: Mistral Nemo
API Model ID: mistralai/mistral-nemo
Category: Text To Text
Description: Mistral Nemo is a 12B parameter model built jointly by Mistral AI and NVIDIA. It offers a 128K context window and serves as an efficient drop-in replacement for smaller models. **Key Features:** - 128K token context window - 12B parameters (FP8 quantized) - Multilingual: English, French, German, Spanish, Italian, Portuguese, Russian, Chinese, Japanese - Function calling and tool use - JSON structured outputs **Capabilities:** - Text generation and chat - Code generation and debugging - Translation and multilingual tasks - Function/tool calling **Best For:** - Cost-effective text generation - Multilingual applications - Lightweight deployment scenarios - High-throughput inference **Technical Specs:** - Architecture: Transformer with 40 layers, 5120 dimensions - License: Apache 2.0
Context Window: 131,072 tokens
Max Output: 8,192 tokens
How to Use This Model
To use Mistral Nemo via the HInow.ai API, use the model ID: mistralai/mistral-nemo
API Request Example (Chat/Text)
POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "mistralai/mistral-nemo",
"messages": [
{"role": "user", "content": "Your message here"}
]
}
Pricing
- input: $0.034
- output: $0.068
Available Parameters
- temperature: Controls randomness (0-1.5). Default: 0.7 (Options: 0, 0.3, 0.5, 0.7, 1.0, 1.5)
- top_p: Nucleus sampling (0-1). Default: 1 (Options: 0.1, 0.5, 0.7, 0.9, 0.95, 1.0)
- max_tokens: Max tokens to generate (Options: 256, 512, 1024, 2048, 4096, 8192)
- response_format: Output format (Options: text, json_object)
- stop: Up to 4 sequences where the API stops generating further tokens
Quick Reference
To use this model, set: "model": "mistralai/mistral-nemo"
Featured: No
Documentation: https://hinow.ai/models/mistralai/mistral-nemo
API Endpoint: https://api.hinow.ai/v1
