tokenstat
tokenstat
Inception

Mercury 2

inception/mercury-2 · rates as of · Benchmarks · Plans · Calculator

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Cheapest input
$0.25
$/MTok · models.dev
Cheapest output
$0.75
$/MTok
Context
128K
tokens
Offers
7
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestmercury-2Inception$0.25$0.75$0.025128K
models.devinception/mercury-2Kilo Gateway$0.25$0.75$0.025128K
models.devmercury-2NanoGPT$0.25$0.75$0.025128K
OpenRouterinception/mercury-2OpenRouter$0.25$0.75$0.025128K
models.devinception/mercury-2Vercel AI Gateway$0.25$0.75$0.025128K
LiteLLMmercury-2$0.25$0.75$0.025
models.devmercury-2Venice AI$0.3125$0.9375$0.0313128K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • In: text
  • Out: text
Knowledge cutoff: 2025-01-01Released: 2026-02-24Family: mercury

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash