Mercury 2

Mercury 2 is a reasoning model from Inception for deliberate analysis, multi-step problem solving, and tool use. It is the first version of the mercury line in the registry. It has a 128000 token context window and a 50000 token output limit. Pricing starts at $0.25 per million input tokens and $0.75 per million output tokens, with cached input at $0.025 per million tokens. Weights are not open. It accepts text and returns text, supports reasoning mode and tool calling.

First version of its line in the registry.

Range across the hosts that serve it: up to $0.3125 per 1M input tokens.

• ·Reasoning mode for deliberate analysis
• ·Multi-step problem solving
• ·Tool calling support
• ·128k context window
• ·50k max output tokens

• Reach for it for deliberate analysis tasks
• Reach for it for multi-step problem solving
• Reach for it for tool use workflows

6 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?

128000 tokens.

What is the price?

From $0.25 per million input tokens and $0.75 per million output tokens. Cached input at $0.025 per million.

Are the weights open?

No, the weights are not open.