Mercury Edit 2
Mercury Edit 2 is Inception's second-generation diffusion large language model (dLLM) purpose-built for next-edit prediction, the most latency-sensitive step in modern coding workflows.
text + code → code · made by Inception Labs
$0.25→$0.75per Mtok in / out
Inception Labs
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Inception Labs api | standard | $0.25per Mtok in$0.75per Mtok out$0.025per Mtok cacheddocs.inceptionlabs.ai · read 2026-08-25 |
About
Mercury Edit 2 — a code model from Inception Labs, sold by one company from $0.25 in and $0.75 out per million tokens.
It takes text and code and returns code, with a context window of 32,768 tokens. It was published in March 2026. Its sellers say it can reason step by step. The catalogue files it under code. Only Inception Labs sells it, at $0.25 in and $0.75 out per million tokens.
Every current figure
- Maker
- Inception Labs
- Register
- model
- Takes
- text + code
- Returns
- code
- Context
- 32,768 tokens
- Longest answer
- 8,192 tokens
- Published
- March 2026
- Licence
- not read
- Sellers
- 1
- Price
- $0.25 in and $0.75 out per million tokens — Inception Labs
Known as 1 name
mercury-edit-2