Mercury 2
Inception · released Mar 4, 2026
- Type
- Closed
- Input
- $0.25
- Output
- $0.75
- Cached
- $0.025
List price · per 1M tokens · Inception at 128K context · source ↗
Our take
Written Sep 17, 2026Mercury 2 is a hosted-only text model: we list no download for it, so using it means choosing a host, and both hosts we list charge the same rate. It takes long inputs in one go and scores on six preference boards, none of which measure whether an answer was correct.
Use it for chat, drafting and general text work where a single rate across both hosts keeps the choice simple, or for long inputs that would otherwise have to be split up first. Its coding result is its strongest measured showing of the six boards. Skip it if you need to run the model on your own machine, or if you need measured accuracy rather than preference votes.
The case for it
- Coding prompts are its strongest measured category, above its own results on creative writing, hard prompts, instruction following and web-app building — though that board records which answer people preferred, not whether the code was correct.
- Long documents need not be split up first: the request capacity takes a long report or a stack of documents beside the question, though reliable recall across all of it is unverified in our data.
- Both hosts charge the same rate, so picking between Inception and OpenRouter is not a price decision.
The case against it
- Nothing here measures whether its answers are correct: all six scores come from Arena boards recording preference, so accuracy needs a trial on work you can check yourself.
- Web-app building is its weakest measured category, the lowest of its six board results, and that board also records preference rather than whether the app worked.
- We list no download for it, so hosted use is the only route we can point you to.
How good is it?
A text model for chat and drafting, though it trails most models on everyday questions and prose writing.
- getting answers to everyday questionsArena Text (overall) · 129th of 168
- drafts, rewrites and editingArena Creative Writing · 133rd of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)129th of 168 · 1343
CodingWriting and fixing code on its own
Arena Coding125th of 168 · 1392
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing133rd of 168 · 1292
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Inception, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Inception on 128K of context.
- per 1M tokens
- $0.25 in / $0.75 out
- Context served
- 128K
- Throughput
- ~65 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.25 / $0.75checked 4 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| InceptionThrough OpenRouter | $0.25 / $0.75checked 4 hours ago | 128K50K max reply | 65 tok/s | No | No | Confirmed |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| InceptionThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- inception-mercury-2