o1

o1 is a OpenAI model available in Agent Serve. o1 is a OpenAI model tracked in Agent Serve. It supports a 200k token context window. Pricing starts at $15/1M input tokens and $60/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, medium, high.

o1 starts at $15/1M input tokens, $7.5/1M cached input tokens, and $60/1M output tokens.

o1 supports a context window of 200k 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.

o1 supports the following capabilities in Agent Serve: Tool choice, Structured outputs, Reasoning low, medium, high, Max output 100k.

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.