![Introducing Llama 3.1 inference endpoints in partnership with Meta](/_next/image?url=https%3A%2F%2Fprod-files-secure.s3.us-west-2.amazonaws.com%2Fc285f3eb-d4f2-4ce1-8c53-25d0d3a0337b%2Fea272d4a-ab3c-4b77-a46e-9951c449c9c6%2FFireworks_AI_Guidelines_Graphics2x_%25285%2529.png%3FX-Amz-Algorithm%3DAWS4-HMAC-SHA256%26X-Amz-Content-Sha256%3DUNSIGNED-PAYLOAD%26X-Amz-Credential%3DAKIAT73L2G45HZZMZUHI%252F20240727%252Fus-west-2%252Fs3%252Faws4_request%26X-Amz-Date%3D20240727T062623Z%26X-Amz-Expires%3D3600%26X-Amz-Signature%3Dd4d19d5aa9e0393674411bc30129188f0f5ec20948f40fbc7a4d50412e4b4152%26X-Amz-SignedHeaders%3Dhost%26x-id%3DGetObject&w=2048&q=75&dpl=dpl_FBzHJhPKvev6uqDBeRLNk8irbCQo)
Introducing Llama 3.1 inference endpoints in partnership with Meta
Introducing Llama 3.1 405B, one of the largest open-source models, featuring a 128K context length, support for 10 languages, and powerful tool-calling capabilities, offering a more efficient and customizable alternative to GPT-4o, available as an production-grade API on Fireworks AI.