Mercury 2.5 pricing and specs

Input costs $0.04 per 1M tokens (3.38 ₽) and output costs $0.15 per 1M (12.68 ₽). Inception bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.

List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.04 for input and $0.15 for output by 1,000. The same rates in rubles are 3.38 ₽ and 12.68 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.

The Mercury 2.5 context window is 260K tokens (260,000). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Inception model card as of September 2026.

The context window is 260K tokens (260,000) and a single response is capped at 66K tokens, so longer output has to be generated in parts. Rate limits are set by Inception per account and depend on your plan rather than on the model, so they are not listed here.

Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For Mercury 2.5 that gives 3.38 ₽ per 1M input tokens and 12.68 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.

Mercury 2.5 belongs to the Mercury family at Inception. Models in the Mercury line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Mercury model is listed on the provider page.

Yes, Mercury 2.5 declares a reasoning mode: it works through intermediate steps before it answers. Those steps add output tokens, so a call with a long reasoning chain costs more and takes longer than a plain completion. Capabilities declared for the model: reasoning, tool calling, structured output.

The declared capabilities of Mercury 2.5 are: reasoning, tool calling, structured output. It accepts text as input, and every attachment consumes tokens from the shared context window of 260K tokens. The list comes from the Inception model card and is refreshed with the catalog as of September 2026.