o3

o3 is a Azure OpenAI model available in Agent Serve. o3 is a Azure OpenAI model tracked in Agent Serve. It supports a 200k token context window. Pricing starts at $2/1M input tokens and $8/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, medium, high.

o3 starts at $2/1M input tokens, $0.5/1M cached input tokens, and $8/1M output tokens.

o3 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.

o3 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.