DeepSeek Chat

DeepSeek Chat is a DeepSeek model available in Agent Serve. DeepSeek Chat is a DeepSeek model tracked in Agent Serve. It supports a 1M token context window. Pricing starts at $0.14/1M input tokens and $0.28/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.

DeepSeek Chat starts at $0.14/1M input tokens, $0.003/1M cached input tokens, and $0.28/1M output tokens.

DeepSeek Chat supports a context window of 1M 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 Chat supports the following capabilities in Agent Serve: Temperature 0-2, Tool choice, Structured outputs, Max output 384k.

Best for long-context retrieval, large documents, and high-memory workflows. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.