Meta models on AIgateway — pricing, context, capabilities

SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Meta's transformer-based object detector. Returns bounding boxes + labels.

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

Llama 3.3 70B quantized to fp8 precision, optimized to be faster.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

Llama 3.1 8B quantized to FP8 precision

Classic BART fine-tuned on CNN/DailyMail. Cheap summarization workhorse.

Many-to-many translation across 100 languages without pivoting through English.