Data as of October 25, 2026 · How the score is built
Released Mar 30, 2026128K contextInception Mercury Edit 2 launch post
Mercury Edit 2
Decision readingMercury Edit 2 is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Mar 30, 2026 — see all recent releases
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- mercury-edit-2Inception Mercury Edit 2 launch post
- Context window
- 128KInception Mercury Edit 2 launch post
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- A diffusion next-edit-prediction model served through the Inception API (the blog index dates the launch to March 30, 2026; the post itself carries a September 9, 2026 update stamp). Inception does not publish a context window for the edit model; the value is inherited from the Mercury 2 family.
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.025 per million cached input tokensInception Mercury Edit 2 launch post
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Mercury Edit 2, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Mercury Edit 2 is a proprietary model with a 128K context window. No explicit reasoning mode is documented in this profile.
A diffusion next-edit-prediction model served through the Inception API (the blog index dates the launch to March 30, 2026; the post itself carries a September 9, 2026 update stamp). Inception does not publish a context window for the edit model; the value is inherited from the Mercury 2 family.
Inception reports Mercury Edit 2 as superior on Instinct, fill-in-the-middle, next-edit-prediction, and an internal next-edit benchmark, with a 48% higher acceptance rate and 27% more selective suggestions than its predecessor, but publishes no exact scores, so BenchLM stores no scored rows. The row stays unranked.
The profile has no source-displayable benchmark row yet.
Last updated October 25, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Mercury Edit 2 perform overall in AI benchmarks?
Mercury Edit 2 does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Does Mercury Edit 2 have full benchmark coverage on BenchLM?
No. Mercury Edit 2 currently has 0 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Mercury Edit 2?
Mercury Edit 2 has a documented context window of 128K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.