Loading

Mercury 2.5 – Model Docs — Person.run

Back to docs Concepts reference

Mercury 2.5

Mercury 2.5 is Inception’s diffusion-based reasoning model for chat, agents, and structured workflows, with tool calling, structured outputs, and a 260K context window.

Model overview

Model ID: inception/mercury-2.5
Provider: inception
Type: language
Context window: 260,000 tokens
Max output tokens: 65,536

Tags: implicit-caching, reasoning, tool-use

Model pricing

Metric	Value
`Input tokens (/1M)`	`$0.04`
`Output tokens (/1M)`	`$0.15`
`Image generation`	`n/a`
`Cached input read (/1M)`	`$0.00`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix