AI Prosumer
EN

Model creator

Meta

meta/

Explore models by Meta. Compare available providers, model tags and inference pricing in one place.

Meta develops the Llama family of language and multimodal models. Llama 4 model weights are distributed under the Llama 4 Community License.

Models

Prices per 1M tokens

meta/llama3.1

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

93 model tags131K contextToken exchange
Model details

meta/llama2

Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

102 model tags4K contextToken exchange
Model details

meta/llama-guard3

Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.

33 model tags131K contextToken exchange
Model details

meta/llama3.3

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

14 model tags131K contextToken exchange
Model details

meta/llama3.2-vision

Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

9 model tags131K contextToken exchange
Model details

meta/llama-4-maverick

Llama-4-Maverick-17B-128E-Instruct-FP8 is a model by Meta that accepts text and images and produces text. This catalog entry identifies meta/llama-4-maverick-17b-128e-instruct-fp8. Its reviewed context window is 1,048,576 tokens; deployment limits can be lower.

1M contextToken exchange
Model details