Mercury 2.5 Preview
NEWInception · Proprietary · Released Aug 31, 2026 · inception/mercury-2.5-preview
Best $0.04 in / $0.15 out via Inception
260K contextToolsReasoningStructured outputPrompt caching
Available from 1 providerUSD / MTOK · PRICES 17 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| INInception1ST PARTY | $0.04 | $0.15 | $0.004 | 260K | — | — | — | 100.0% |
Pricing variants · USD / MTok in / out
STANDARD
$0.04 / $0.15
per MTok in / out
CACHE READ $0.004
Recent changesRSS ↗
Sep 2, 2026model added
About
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Specifications
Context window260,000
Max output65,536
Modalities intext
Modalities outtext
LicenseProprietary
ReleasedAug 31, 2026
TokenizerOther
Related
Embed badge
[](https://modelindex.ai/models/inception/mercury-2.5-preview)Sources
OpenRouter API17 minutes ago
AGGREGATORVerified 17 minutes ago · list prices, not negotiated rates.