All Models

Mercury 2

mercuryReasoningTool CallingStructured Output

Compact GPT model for low-latency assistance and high-volume workloads

Providers6
ReleasedJan 1, 2024
Input Modalitiestext
Output Modalitiestext
Tarsk Usecoding

Benchmarks

13.8
Intelligence Index
31.1
Coding Index

Available Providers (6)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
NanoGPTmercury-2$0.25/MTok$0.75/MTok128K50K
Vercel AI Gatewayinception/mercury-2$0.25/MTok$0.75/MTok128K128K
Inceptionmercury-2$0.25/MTok$0.75/MTok128K50K
Kilo Gatewayinception/mercury-2$0.25/MTok$0.75/MTok128K50K
OpenRouterinception/mercury-2$0.25/MTok$0.75/MTok128K50K
Venice AImercury-2$0.31/MTok$0.94/MTok128K50K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output