DeepSeek V3 2

DeepSeek V3 2 is a AWS Bedrock model available in Agent Serve. DeepSeek V3 2 is a AWS Bedrock model tracked in Agent Serve. It supports a 164k token context window. Pricing starts at $0.62/1M input tokens and $1.85/1M output tokens. Key capabilities include Tool choice, Structured outputs, Max output 8k.

DeepSeek V3 2 starts at $0.62/1M input tokens, and $1.85/1M output tokens.

DeepSeek V3 2 supports a context window of 164k 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.

DeepSeek V3 2 supports the following capabilities in Agent Serve: Tool choice, Structured outputs, Max output 8k.

Best for production workflows that need reliable typed outputs. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.