Models

Multilingual 70B instruction-tuned model with performance close to much larger models on reasoning, math and general knowledge.

meta/llama-3.3-70b-instruct128K context$0.72/M input$0.72/M output

Mixture-of-experts multimodal model with 128 experts and a 1M-token context window, tuned for assistant and chat use cases.

meta/llama-4-maverick1.0M context$0.24/M input$0.97/M output