Llama 3.1 Nemotron 70B Instruct

Llama 3.1 Nemotron 70B Instruct is a NVIDIA NIM model available in Agent Serve. Llama 3.1 Nemotron 70B Instruct is a NVIDIA NIM model tracked in Agent Serve. It supports a 128k token context window. Pricing starts at $1.2/1M input tokens and $1.2/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.

Llama 3.1 Nemotron 70B Instruct starts at $1.2/1M input tokens, and $1.2/1M output tokens.

Llama 3.1 Nemotron 70B Instruct supports a context window of 128k tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

Llama 3.1 Nemotron 70B Instruct supports the following capabilities in Agent Serve: Temperature 0-2, Tool choice, Structured outputs, Max output 4k.