Provider logo

Mercury 2

mercury-2
Provider logo

Mercury 2

mercury-2

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

Context Window

128.0K

Max Output

50.0K

Avg output tokens (7d)

2.3K tokens

97%

Input Price (Auto)

$0.25/1M

Output Price (Auto)

$0.75/1M

Cache Read (Auto)

$0.025/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

14.9

Better than 56% of models compared

Coding Index

31.1

Better than 39% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

77.0%

Better than 61% of models compared

HLE

Humanity's Last Exam

17.1%

Better than 69% of models compared

IFBench

Instruction-following benchmark

69.8%

Better than 84% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

70.8%

Better than 63% of models compared

AA-LCR

Long context reasoning evaluation

43.7%

Better than 42% of models compared

Coding

Terminal-Bench Hard

Agentic coding and terminal use

26.5%

Better than 68% of models compared

Last updated Sep 7, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Mercury 2 with similar models from the same provider or model family.

Mercury 2.5 Preview

inception/mercury-2.5-preview

Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.

Mercury Coder Small

mercury-coder-small

Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.

DeepSeek V4 Flash Vision Exp Uncensored

deepseek/deepseek-v4-flash-vision-exp-uncensored

An uncensored variant of the experimental vision-enabled DeepSeek V4 Flash model for chat, image understanding, reasoning, coding, and tool use, with a 524K context window.

TheDrummer/Artemis v1.1

TheDrummer/Artemis-v1.1

TheDrummer's Artemis v1.1 is a Gemma 4 31B fine-tune for creative writing, expressive dialogue, and roleplay, with optional thinking and a 262K context window.

Synth 2.5 Flash Preview

synth-2.5-flash

Synth 2.5 Flash Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.

Synth 2.5 Pro Preview

synth-2.5-pro

Synth 2.5 Pro Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.