Inception model product
Mercury 2
Mercury 2 is a reasoning LLM from Inception built on diffusion-based language model (dLLM) architecture, with tool usage, JSON output, and a 128K context window.
Updated Sep 8, 2026. Default version: Mercury 2
LLMBoard Score37.8Mercury 2
Coverage0%6 benchmark families
Context window128KTokens
Official input price$0.25Inception API
Mercury 2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Mercury 2 Benchmark Results
Benchmark scores for Mercury 2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSciCode | Score38.00% | Rank18 | Participants24 | Percentile26.09% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score53.00% | Rank20 | Participants24 | Percentile17.39% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score71.00% | Rank23 | Participants39 | Percentile42.11% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score67.00% | Rank26 | Participants75 | Percentile66.22% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score91.10% | Rank44 | Participants119 | Percentile63.56% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,166.19 rating | Rank94 | Participants97 | Percentile3.13% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,371.21 rating | Rank114 | Participants121 | Percentile5.83% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score74.00% | Rank124 | Participants247 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,357.63 rating | Rank130 | Participants210 | Percentile38.28% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,346.51 rating | Rank147 | Participants210 | Percentile30.14% | EvidenceA | Evaluated |
Mercury 2 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenawebdev | Categorywebdev-react | Rank82 | Rating / score1,155.25 | Votes804 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank93 | Rating / score1,198.57 | Votes103 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank94 | Rating / score1,166.19 | Votes908 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank94 | Rating / score1,166.19 | Votes908 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank112 | Rating / score1,392.82 | Votes1,128 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank114 | Rating / score1,412.02 | Votes200 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank114 | Rating / score1,340.06 | Votes2,117 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank114 | Rating / score1,386.30 | Votes1,743 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank114 | Rating / score1,349.83 | Votes1,872 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank114 | Rating / score1,371.21 | Votes3,042 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank123 | Rating / score1,390.52 | Votes758 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank123 | Rating / score1,382.34 | Votes1,170 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank124 | Rating / score1,351.85 | Votes479 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank125 | Rating / score1,385.49 | Votes1,054 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank126 | Rating / score1,368.69 | Votes225 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank127 | Rating / score1,401.79 | Votes200 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank128 | Rating / score1,356.76 | Votes518 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank129 | Rating / score1,376.48 | Votes701 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank129 | Rating / score1,321.32 | Votes655 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank130 | Rating / score1,357.63 | Votes3,043 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank132 | Rating / score1,356.23 | Votes233 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank132 | Rating / score1,362.83 | Votes1,743 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank133 | Rating / score1,315.63 | Votes2,118 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank135 | Rating / score1,332.42 | Votes1,873 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank138 | Rating / score1,324.24 | Votes839 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank139 | Rating / score1,350.24 | Votes461 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank141 | Rating / score1,331.37 | Votes844 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank141 | Rating / score1,393.71 | Votes758 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank142 | Rating / score1,370.14 | Votes1,170 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank142 | Rating / score1,315.47 | Votes655 | ObservationsN/A | Result date |
Mercury 2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.25 input, $0.75 output per 1M
- Official provider
- Inception
- Lowest third-party
- From $0.25 input, $0.75 output per 1M via NanoGPT
- Tracked offerings
- 5
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNanoGPT | Provider model IDmercury-2 | Regionglobal | Input / 1M$0.25 | Output / 1M$0.75 | Context128K | Updated |
| ProviderInception | Provider model IDmercury-2 | Regionglobal | Input / 1M$0.25 | Output / 1M$0.75 | Context128K | Updated |
| ProviderOpenRouter | Provider model IDinception/mercury-2 | Regionglobal | Input / 1M$0.25 | Output / 1M$0.75 | Context128K | Updated |
| ProviderVercel AI Gateway | Provider model IDinception/mercury-2 | Regionglobal | Input / 1M$0.25 | Output / 1M$0.75 | Context128K | Updated |
| ProviderVenice AI | Provider model IDmercury-2 | Regionglobal | Input / 1M$0.3125 | Output / 1M$0.9375 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Mercury 2 Runtime Performance
Provider-specific output speed and catalog latency for Mercury 2. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderInception | Output Speed346.33 tok/s | Catalog Latency1.64 s | Max Input128K | Max Output8.2K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Mercury 2 Specifications
Technical details for the model's default version.
- Version
- Mercury 2
- Released
- Feb 24, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 128K
- Max output
- 8.2K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Mercury 2 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMercury 2 | Released | LLMBoard37.76 | ParametersN/A | Context128K | Max output8.2K | Open weightsNo | LicenseProprietary |
Models similar to Mercury 2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 3.7
Anthropic
ZA
GLM 4.7 Flash
Zhipu AI
NV
Nemotron 3.5 Lightning
NVIDIA
GO
Google
Gemma 4 12B
GOGoogle
Gemini 2.5 Flash
AN
Claude Sonnet 4
Anthropic
What is Mercury 2?
Key information about Mercury 2 and its available data.
Mercury 2 is a reasoning LLM from Inception built on diffusion-based language model (dLLM) architecture. It refines multiple text blocks simultaneously rather than generating text token-by-token and supports tool usage, JSON output, and a 128K context window.
Data as of 2026-09-08.
FAQ
Common questions about Mercury 2.
When was Mercury 2 released?
Mercury 2's default version was released on Feb 24, 2026.
How much does Mercury 2 cost?
Mercury 2's official API price is $0.25 per million input tokens and $0.75 per million output tokens via Inception. The lowest tracked third-party offer starts at $0.25 input and $0.75 output via NanoGPT.
Who created Mercury 2?
Mercury 2 was created by Inception.
What is the context window for Mercury 2?
The default version has a 128K token context window.
Is Mercury 2 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Mercury 2?
5 provider offerings are linked to the default version.