Meta AI

Creator of the Llama model family — open-weight models available via multiple providers. Llama 4 Scout and Maverick are multimodal with strong OCR performance.

Models on OpenOCR

Available now

~1,560 pages / $1~$0.00064 per standard page

Lowest reference cost

Available Models

Meta: Llama 4 MaverickLLM Vision

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

~1,560 pages / $1~$0.00064 per standard page

4862ms

Meta: Llama 4 ScoutLLM Vision

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.

~1,370 pages / $1~$0.000731 per standard page

1576ms

Coming Soon

Llama 4 Maverick (Together)

Meta's latest Llama 4 Maverick model hosted on Together AI. Large mixture-of-experts architecture with strong vision and document understanding capabilities.

Coming Soon