Mercury 3
NEWInception · Proprietary · Released Oct 16, 2026 · inception/mercury-3
Best $0.10 in / $0.35 out via Inception
1M contextToolsReasoningStructured outputPrompt caching
Available from 1 providerUSD / MTOK · PRICES 24 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.10 | $0.35 | $0.01 | 1M | — | — | — | 99.9% |
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.10 / $0.35
per MTok in / out
CACHE READ $0.01
Recent changesRSS ↗
Oct 20, 2026model added
About
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
Specifications
Context window1,000,000
Max output131,072
Modalities intext
Modalities outtext
LicenseProprietary
ReleasedOct 16, 2026
TokenizerOther
Embed badge
[](https://modelindex.ai/models/inception/mercury-3)Sources
OpenRouter API24 minutes ago
AGGREGATORVerified 24 minutes ago · list prices, not negotiated rates.