Models/Inception/Mercury 2

Mercury 2

Name: Mercury 2 API access
Brand: Inception

Inception · Proprietary · Released Mar 4, 2026 · inception/mercury-2

Best $0.25 in / $0.75 out via Inception

Compare Estimate cost

128K contextToolsReasoningStructured outputPrompt caching

Available from 1 providerUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 2 DAYS AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Inception1ST PARTY	$0.25	$0.75	$0.025	128K	—	✕	✕	100.0%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 2 days ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

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

Mercury 2.5$0.04 / $0.15

Embed badge

[![Mercury 2](https://modelindex.ai/badge/inception/mercury-2)](https://modelindex.ai/models/inception/mercury-2)

Sources

OpenRouter API23 minutes ago

AGGREGATOR

LiteLLM dataset23 minutes ago

AGGREGATOR

ModelIndex benchmarks2 days ago

MEASURED

Verified 23 minutes ago · list prices, not negotiated rates.