Mercury 3
by Inceptiontext->text
Neura Intelligence Index
85.4/ 100
Rank
#26—
Confidence
lowBenchmarks
1(3% coverage)
Overview
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...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Stop sequences
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
1M tokens
Max Output
131.1K tokens
Tokenizer
Other
Country
🇺🇸US
Release Date
October 19, 20264d
Supported Parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetools
Performance Over Time
Pricing
Per 1M tokens
Input$0.10
Output$0.35
Cache read$0.01
Added
October 16, 2026
Last synced 10/23/2026