L

Llama Models

Browse models from Llama
Llama is Meta's advanced open-source AI model family. The latest Llama 4 features a mixture-of-experts architecture, supports 10 million token context length, native multimodality, and matches GPT-4 performance. Freely available for download, it empowers developers worldwide to build innovative AI applications without vendor lock-in.
L

Llama-4-Scout

L

Llama-4-Scout

Input:$0.216/M
Output:$1.152/M
Llama-4-Scout is a general-purpose language model for assistant-style interaction and automation. It handles instruction following, reasoning, summarization, and transformation tasks, and can support light code-related assistance. Typical uses include chat orchestration, knowledge-augmented QA, and structured content generation. Technical highlights include compatibility with tool/function calling patterns, retrieval-augmented prompting, and schema-constrained outputs for integration into product workflows.
L

Llama-4-Maverick

L

Llama-4-Maverick

Input:$0.48/M
Output:$1.44/M
Llama-4-Maverick is a general-purpose language model for text understanding and generation. It supports conversational QA, summarization, structured drafting, and basic coding assistance, with options for structured outputs. Common applications include product assistants, knowledge retrieval front-ends, and workflow automation that require consistent formatting. Technical details such as parameter count, context window, modality, and tool or function calling vary by distribution; integrate according to the deployment’s documented capabilities.