Llama Guard 4 is a natively multimodal 12B safety classifier for classifying prompts and responses as safe or unsafe.
meta-llama/llama-guard-4-12bApr 28, 20255 Meta models on FastRouter, all behind one OpenAI-compatible API. Compare pricing, context windows and benchmarks, then open any model for its providers and code samples.
Llama Guard 4 is a natively multimodal 12B safety classifier for classifying prompts and responses as safe or unsafe.
meta-llama/llama-guard-4-12bApr 28, 2025Llama-4-Scout-17B-16E-Instruct is a multimodal, instruction-tuned language model developed by Meta, designed to handle long-context tasks efficiently. It features 17 billion active parameters with a total of 109 billion parameters across 16 experts, utilizing a mixture-of-experts (MoE) architecture. The model supports a context window of up to 10 million tokens, making it suitable for applications requiring extensive context, such as multi-document summarization and large codebase exploration.
meta-llama/llama-4-scout-17b-16e-instructFeb 12, 2025Llama 3.1 8B Instruct is Meta's compact, efficiency-focused language model from the Llama 3.1 family. At just 8 billion parameters, this instruction-tuned variant delivers impressive performance with minimal computational requirements, making it ideal for resource-constrained environments and latency-sensitive applications. Despite its smaller size, the model maintains competitive performance in human evaluations against much larger models, particularly excelling in straightforward dialogue, content generation, and common instruction-following tasks. The model features improved inference speed and reduced deployment costs compared to larger variants while maintaining the core capabilities that make Llama models effective. It's particularly well-suited for mobile applications, edge devices, and scaled deployments where efficiency and performance balance are critical considerations.
meta-llama/llama-3.1-8b-instantFeb 12, 2025Llama 3.3 70B Turbo is an FP8-quantized version of Llama 3.3 70B for significantly faster inference with a minor accuracy trade-off.
meta-llama/llama-3.3-70b-instruct-turboDec 6, 2024Meta Llama 3.1 8B Instruct, served in an FP8 Turbo configuration.
meta-llama/llama-3.1-8b-instruct-turboJul 23, 2024Model scores sourced from ArtificialAnalysis