Catalogue
Models
376 models, cross-linked to hardware verdicts and live provider pricing.
8 models
Llama Guard 4 12BMetaLlama Guard 4 is a 12-billion-parameter safety classifier from Meta that reads text and images to judge content safety.Apr 202512B1M$0.18 / $0.18per 1Mvia OpenRouter—
Llama7 sizes here
Llama 4 ScoutMetaLlama 4 Scout is a 109-billion-parameter text-and-image model from Meta with a 1.3-million-token request limit, released in 2025.Apr 2025109B1.3M$0.10 / $0.30per 1Mvia OpenRouter—Llama 4 MaverickMetaLlama 4 Maverick is a large downloadable model from Meta that accepts text and images and can handle up to one million tokens in a single request.Apr 2025402B1M$0.20 / $0.80per 1Mvia OpenRouter—Llama 3.3 70B InstructMetaLlama 3.3 is a 70.6-billion-parameter text model from Meta with a 131,072-token request limit and a licence that permits commercial use with specific conditions.Nov 202470.6B131K$0.10 / $0.32per 1Mvia OpenRouter—Llama 3.2 1B InstructMetaLlama 3.2 1B Instruct is Meta's smallest instruction-tuned model, a 1.2-billion-parameter text model released in 2024 for edge deployment and cost-sensitive inference.Sept 20241.2B60K$0.020 / $0.020per 1Mvia Novita AI—Llama 3.2 3B InstructMetaLlama 3.2 is a tiny text-only model from Meta that can handle up to 131,072 tokens in a single request — an unusually long reach for something this small.Sept 20243.2B131K$0.050 / $0.33per 1Mvia OpenRouter—Llama 3.1 8B InstructMetaLlama 3.1 is a compact downloadable model from Meta with a 131,072-token request limit and a licence that restricts large-scale commercial use.Jul 20248B131K$0.050 / $0.080per 1Mvia OpenRouter—Llama 3.1 70B InstructMetaLlama 3.1 is a 70.6-billion-parameter text model from Meta, released in 2024 with a restricted community licence.Jul 202470.6B131K$0.40 / $0.40per 1Mvia OpenRouter—