Skip to content
Sovyron

Mercury 2.5

mercury260k context66k max outputreleased Sep 1, 2026ReasoningTool calling

As of Nov 22, 2026, the cheapest Mercury 2.5 API price is $0.04 per 1M input tokens (NanoGPT) and $0.15 per 1M output tokens (NanoGPT). Mercury 2.5 is offered by 2 providers in the mercury family, reasoning enabled.

Cheapest input
$0.04
Cheapest output
$0.15
Official
—
output per 1M tokens
Providers
2
offering this model
Spread
5.0×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Mercury 2.5 API prices by provider in USD per 1M tokens, updated Nov 22, 2026
NanoGPTinception/mercury-2.5-previewCheapest$0.04Cheapest$0.15$0.004—260k—
Inceptionmercury-2.5$0.2$0.75$0.02—260k31d ago

Mercury 2.5 price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.

Mercury 2.5 output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.25$0.5$0.75$1Sep 10, 2026Oct 17, 2026Nov 22, 2026
Inception$0.75
Mercury 2.5 price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Inception$0.04 → $0.2$0.15 → $0.75+400%

Mercury 2.5 pricing FAQ

What is the cheapest Mercury 2.5 API?

As of Nov 22, 2026, NanoGPT has the lowest Mercury 2.5 output price at $0.15 per 1M tokens, and NanoGPT has the lowest input price at $0.04 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Mercury 2.5?

2 providers list Mercury 2.5 on Sovyron; 2 of them sell it at a metered per-token price.

Is Mercury 2.5 free?

No provider in the Sovyron catalog lists a free tier for Mercury 2.5.

What is the context window of Mercury 2.5?

Mercury 2.5 supports a 260k-token context window and up to 66k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—