Using Llama 3.1 405B Instruct on OctoAI API (Deprecated)
Implementation guide · Llama 3.1 · AI at Meta
Quick Start
- 1Create an account at OctoAI API (Deprecated) and generate an API key.
- 2Use the OctoAI API (Deprecated) SDK or REST API to call
llama3.1-405b-instruct.
Code Examples
About OctoAI API (Deprecated)
No public independent OctoAI API, model catalog, portal, documentation, or pricing surface was verified on the former OctoAI routes checked. Those routes redirect to NVIDIA’s general site; do not treat that site as a successor to the former OctoAI API.
OctoAI was a hosted inference platform for running third-party foundation models. OctoAI’s company profile states that NVIDIA acquired it in September 2024 and that it was dissolved as an independent corporate entity. This entry is retained only as historical provider coverage.
Pricing on OctoAI API (Deprecated)
Capabilities
About Llama 3.1 405B Instruct
Llama 3.1 405B Instruct is Meta's advanced large language model released on July 23, 2024, featuring 405 billion parameters. It utilizes an optimized transformer architecture with supervised fine-tuning and reinforcement learning for enhanced instruction-following capabilities. The model supports multiple languages, was trained on 15 trillion tokens, and fine-tuned with 25 million synthetic examples. It excels in multilingual dialogue and text generation, making it ideal for assistant-like applications. Llama 3.1 incorporates robust safety measures and ethical considerations, outperforming many existing models on various industry benchmarks. AI engineers can access the model via its Hugging Face page for implementation in diverse NLP tasks.