o3-pro

o3-pro is a high-effort tier for difficult technical reasoning and careful answers. It is the first version of the o-pro line in the registry. It has a context window of 200,000 tokens and a maximum output of 100,000 tokens. Pricing starts at $18.00 per million input tokens and $40.00 per million output tokens, with cached input at $11.00 per million. The weights are not open. It supports reasoning mode, tool calling, accepts image and text, and returns text. Knowledge cutoff is May 2024. It is served by 9 hosts.

First version of its line in the registry.

Range across the hosts that serve it: up to $22.00 per 1M input tokens.

• ·Handles 200k token context window
• ·Generates up to 100k output tokens
• ·Supports tool calling and reasoning mode
• ·Accepts image and text inputs
• ·Served by 9 hosts for availability

• Reach for it for difficult technical reasoning
• Reach for it for careful answers on complex problems
• Reach for it for long-context analysis with image input
• Reach for it for tool-assisted problem solving

9 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 200,000 tokens.

What is the price per token?

From $18 per million input tokens and $40 per million output tokens, with cached input at $11 per million.

Can it process images?

Yes, it accepts image and text inputs and returns text.