Mercury 2

reasoningproprietary

Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury's speed means that users can stay in the flow, enjoying rapid chat-based iteration and responsive completion suggestions. On Copilot Arena, Mercury ranks 1st in speed and ties for 2nd in quality.

Context
128K
Max output
50K
Input price
$0.25/1M tokens
Output price
$0.75/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDmercury-2
Provider Inception Labs
Creator inception
Familymercury
Licenseproprietary
Statusactive
Typereasoning
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window128K tokens
Max input—
Max output50K tokens
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.inceptionlabs.ai/v1/chat/completions

Pricing

Input
$0.25
Output
$0.75
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

Family Comparison: mercury

ModelContextMax outPricing
Mercury Decide66K50K$0.02$0
Mercury 31M131K$0.1$0.35
Mercury 2.5260K66K$0.2$0.75
Mercury 2128K50K$0.25$0.75
Mercury Coder128K32K$0.25$0.75
Mercury Edit 2128K32K$0.25$0.75
Mercury Edit128K32K$0.25$0.75
Mercury128K32K$0.25$0.75

API

GET/v1/models/inception/mercury-2