DeepSeek R1

DeepSeek R1 is a DeepSeek model available in Agent Serve. DeepSeek R1 is a DeepSeek model tracked in Agent Serve. It supports a 128k token context window. Pricing starts at $0.55/1M input tokens and $2.19/1M output tokens. Key capabilities include Tool choice, Structured outputs, Thinking enabled.

DeepSeek R1 starts at $0.55/1M input tokens, $0.14/1M cached input tokens, and $2.19/1M output tokens.

DeepSeek R1 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.

DeepSeek R1 supports the following capabilities in Agent Serve: Tool choice, Structured outputs, Thinking enabled.

Best for reasoning-heavy tasks that need more deliberate model control. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.