inception Reasoning

Mercury 2 pricing & benchmarks

Released Mar 4, 2026 · served by 1 provider

Input / 1M tokens$0.250
Output / 1M tokens$0.750
Context window128K
Cached input$0.025
Intelligence index21.4
Coding index31.1
Agentic index9.6
1M in + 300K out$0.47

What Mercury 2 is

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...

Providers and prices for Mercury 2

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Inceptioncheapest $0.250 $0.750 128K 100.0%

Mercury 2 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
asciiart models #54 1044 28.2%
svg models #71 1028 25.2%
3d models #92 1040 23.9%
gamedev models #94 1032 21%
dataviz models #96 1007 20.9%
uicomponent models #96 995 18.5%
codecategories models #102 1020 20.6%
website models #105 1010 19.5%

Cheaper models in the same class

Models scoring within 4 points of Mercury 2 on the Intelligence Index, but with a lower output price.

FAQ

How much does the Mercury 2 API cost?

$0.250 per 1M input tokens and $0.750 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.47.

Is Mercury 2 free?

No. It is a paid model starting at $0.250 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Mercury 2?

Inception at $0.250 input / $0.750 output per 1M tokens.

Can I self-host Mercury 2?

No. Mercury 2 is closed-weight and only available through hosted APIs.