Inception

13 indexed models

13 matching models

Inception: Mercury 2

inception/mercury-2-20260304

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...

Context window
128,000
Input modalities
text
Output modalities
text

Benchmarks

  • Artificial Analysis: 10.8

Inception: Mercury 2.5

inception/mercury-2.5-20260908

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

Context window
260,000
Input modalities
text
Output modalities
text

Benchmarks

  • Artificial Analysis: 12.3

Inception: Mercury 3

inception/mercury-3-20261019

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...

Context window
1,000,000
Input modalities
text
Output modalities
text

Inception: Mercury Decide

inception/mercury-decide-20260930

Mercury Decide is Inception's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no...

Context window
65,536
Input modalities
text, image
Output modalities
decisions

mercury-2

cheaperInference/mercury-2

Context window
128,000
Maximum output
128,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Mercury 2

vercelAIGatewayCatalog/inception/mercury-2

A diffusion-based reasoning LLM that generates text via parallel refinement (not token-by-token), delivering real-time latency with ~1k tokens/sec plus 128K context and built-in tool/JSON support.

Context window
128,000
Maximum output
128,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

mercury-2.5

cheaperInference/mercury-2.5

Context window
260,000
Maximum output
65,536
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Mercury 2.5

vercelAIGatewayCatalog/inception/mercury-2.5

Mercury 2.5 is Inception’s diffusion-based reasoning model for chat, agents, and structured workflows, with tool calling, structured outputs, and a 260K context window.

Context window
260,000
Maximum output
65,536
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Inference prices

Mercury 2 · azureml-inceptionlabs v1

azureFoundry/azureml-inceptionlabs/Mercury-2@1

State-of-the-art diffusion based reasoning model.

Context window
128,000
Maximum output
50,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, toolCalling

mercury-3

cheaperInference/mercury-3

Context window
1,000,000
Maximum output
131,072
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Mercury 3

vercelAIGatewayCatalog/inception/mercury-3

Mercury 3 is Inception’s most capable model for agentic workflows and real-time applications. It is one of the world’s fastest models, powered by diffusion.

Context window
1,000,000
Maximum output
131,072
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Inference prices

Mercury · azureml-inceptionlabs v1

azureFoundry/azureml-inceptionlabs/Mercury@1

Mercury is a diffusion LLM (dLLM) that generates text in parallel, yielding a 5-10X speed-up for coding workflows.

Input modalities
text
Output modalities
text

mercury-coder-small

cheaperInference/mercury-coder-small

Context window
32,000
Maximum output
16,384
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace