DeepSeek V4 Pro is a DeepSeek model tracked in Sim. It supports a 1M token context window. Pricing starts at $1.32/1M input tokens and $3.96/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, high, max. Best for reasoning-heavy tasks that need more deliberate model control.
Best forBest for reasoning-heavy tasks that need more deliberate model control.
TemperatureNot configurable
Reasoning effortlow, high, max
VerbosityNot supported
Thinking levelsnone, enabled (default: enabled)
Structured outputsSupported
Tool choiceSupported
Computer useNot supported
Deep researchNot supported
Memory supportSupported
Max output tokens384k
Frequently asked questions
DeepSeek V4 Pro is a DeepSeek model available in Sim. DeepSeek V4 Pro is a DeepSeek model tracked in Sim. It supports a 1M token context window. Pricing starts at $1.32/1M input tokens and $3.96/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, high, max.
DeepSeek V4 Pro starts at $1.32/1M input tokens, $0.044/1M cached input tokens, and $3.96/1M output tokens.
DeepSeek V4 Pro supports a context window of 1M tokens in Sim. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.
DeepSeek V4 Pro supports the following capabilities in Sim: Tool choice, Structured outputs, Reasoning low, high, max, Thinking none, enabled, Max output 384k.
Best for reasoning-heavy tasks that need more deliberate model control. When used in a Sim workflow, it can be selected in any Agent block from the model picker.
