Mercury 2
Inception · Proprietary · Released Mar 4, 2026 · inception/mercury-2
128K contextToolsReasoningStructured outputPrompt caching
Available from 1 providerUSD / MTOK · VERIFIED 13 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| INInception1ST PARTY | $0.25 | $0.75 | $0.025 | 128K | — | 1.5s | — | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 45 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.25 / $0.75
per MTok in / out
CACHE READ $0.025
About
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...
Specifications
Context window128,000
Max output50,000
Modalities intext
Modalities outtext
LicenseProprietary
ReleasedMar 4, 2026
TokenizerOther
Embed badge
[](https://modelindex.ai/models/inception/mercury-2)Sources
OpenRouter API13 minutes ago
AGGREGATORLiteLLM dataset13 minutes ago
AGGREGATORModelIndex benchmarks45 hours ago
MEASUREDVerified 13 minutes ago · list prices, not negotiated rates.