Mercury 2
Inception · released Mar 4, 2026
- Type
- Proprietary
- Input
- $0.25
- Output
- $0.75
- Cached
- $0.025
List price · per 1M tokens · Inception at 128K context · source ↗
Our take
Written Aug 3, 2026Mercury 2 is a proprietary text model from Inception with a 128,000-token request limit and measured coding skills on the Arena leaderboard. It is a mid-tier specialist with only two hosting options and no downloadable weights.
Pick this when Arena Coding Elo around 1396 is the quality signal you need, or for long-context text work up to 128,000 tokens. Use it if Inception's own endpoint at 222 tokens per second is acceptable and you want OpenRouter as a fallback. Skip it if you need web-development coding, creative writing, or any price competition between providers.
The case for it
- Strongest measured skill is general coding on the Arena leaderboard, well above its own web-development score.
- Identical pricing across both providers, so there is no price arbitrage to hunt.
- Known throughput of 222 tokens per second on Inception's own hosting.
The case against it
- Web-development coding lags its general coding by a wide margin on the same leaderboard.
- Creative writing is its weakest measured skill, nearly a hundred points below its hard-prompts score.
- Only two tracked offers with identical pricing and no disclosed licence; you cannot download, self-host, or find a cheaper alternative.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)103rd of 143 · 1346.6
CodingWriting and fixing code on its own
Arena Coding101st of 143 · 1396.3
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Mercury 2 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Mercury 2 placed and give it no mark out of five.
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, which is why they get no rating.
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.
Or rent it from someone else
Why this differs from the header. The strip above quotes Inception's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.25 in / $0.75 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.25 / $0.75 | 128K | not measured | Unknown | Unknown | Unknown |
| Inception | $0.25 / $0.75 | 128K | 271 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Inception | ✓ | ✓ | ✓ |
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
Dates behind this page
Prices last checked 9d ago
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 do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- inception-mercury-2