Mercury 2

Inception Labs' fastest reasoning model with tool calling and structured outputs support.

Reasoning
Tool Calling
Structured Output

Pricing

Auto routing · per 1M tokens

Input: $0.25
Output: $0.75
Cache read: $0.025

Compare provider prices

Specifications

Context window: 128K
Max output: 50K
Avg output (7d): 144 tokens; Longer than 10% of models

Benchmarks

Artificial Analysis

LMArena

Vectara

Design Arena

Sourced from Artificial Analysis.

Intelligence Index

13.8

Better than 52% of models compared

Coding Index

31.1

Better than 38% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

1.7%

Better than 18% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

261 Elo

Better than 16% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

498 Elo

Better than 26% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

43.7%

Better than 39% of models compared

Reasoning

HLE

Humanity's Last Exam

17.1%

Better than 64% of models compared

IFBench

Instruction-following benchmark

69.8%

Better than 84% of models compared

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

0.0%

Better than 16% of models compared

SciCode

Python programming for scientific computing

37.7%

Better than 19% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

77.0%

Better than 61% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

26.5%

Better than 68% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

70.8%

Better than 63% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation