Mercury Edit 2

Inception Labs
Mercury Edit 2 cover image
Context
32Ktokens
Released
7mo ago

Mercury Edit 2 is a diffusion language model (dLLM) from Inception that succeeds the company's previous next-edit model. Inception bills it as a next-edit diffusion LLM built for the speed-critical parts of coding, saying it generates tokens in parallel so edit suggestions arrive quickly. The model is made for code editing, predicting a developer's next change from recent edit history and codebase context.

How it compares

Vs. your stack

Add the models you use to see how this one compares.

Sign in
Vs. what you use
Is Mercury Edit 2 better than what you use?BetterSameWorse

No verdicts yet

Discussion

Sign in to join the discussion

No comments yet

Be the first to share your thoughts.

Additional source evidence
Source model
inception/mercury-edit-2
Source family
mercury
Last updated
2026-03-30
Model context
32K
Model output limit
8K
Open weights
No
File attachments
No
Reasoning
No
Tool calling
No
Temperature control
Yes
Complete source record (JSON)
{
  "id": "inception/mercury-edit-2",
  "name": "Mercury Edit 2",
  "description": "Code editing dLLM for autocomplete (FIM) and next-edit suggestions",
  "family": "mercury",
  "last_updated": "2026-03-30",
  "attachment": false,
  "reasoning": false,
  "tool_call": false,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 32000,
    "output": 8192
  },
  "release_date": "2026-03-30",
  "open_weights": false
}

Frequently asked questions

Capabilities and specs

Quality and benchmarks

Generated from Vertical Tabs data, updated November 10, 2026.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.