Inception model product
Mercury 2
Mercury 2 is the fastest reasoning LLM, built on diffusion-based language model (dLLM) architecture.
Updated Aug 17, 2026. Default version: Mercury 2
LLMBoard Score38.7Mercury 2
Coverage80%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 | Score38.0% | Rank17 | Participants21 | Percentile20.0% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score71.0% | Rank18 | Participants34 | Percentile48.5% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score53.0% | Rank19 | Participants23 | Percentile18.2% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score67.0% | Rank26 | Participants75 | Percentile66.2% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score91.1% | Rank43 | Participants115 | Percentile63.2% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score74.0% | Rank119 | Participants239 | Percentile50.4% | EvidenceC | 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 | Categoryoverall | Rank112 | Rating / score1166.3 | Votes908 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank147 | Rating / score1371.8 | Votes3,126 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank175 | Rating / score1357.4 | Votes3,127 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank201 | Rating / score1346.4 | Votes3,127 | 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 Speed1,009 tok/s | Catalog Latency1.7 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 | LLMBoard38.7 | ParametersN/A | Context128K | Max output8.2K | Open weightsNo | LicenseProprietary |
Mercury 2 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Mercury 2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 4
Anthropic
GO
Google
Gemini 2.5 Flash
DE
DeepSeek-V3.1
DeepSeek
ZA
GLM 4.7 Flash
Zhipu AI
AN
Claude Sonnet 3.7
Anthropic
OP
GPT-5.3
OpenAI
What is Mercury 2?
Key information about Mercury 2 and its available data.
Mercury 2 is the fastest reasoning LLM, built on diffusion-based language model (dLLM) architecture. Instead of generating text token-by-token, it refines multiple text blocks simultaneously, achieving over 1,000 tokens per second on Nvidia Blackwell GPUs — 5x faster than leading speed-optimized LLMs.
Supports tool usage and JSON output with 128K context window.
Data as of 2026-08-17.
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.
What models should I compare Mercury 2 with?
Nearby ranked alternatives include Qwen3 VL 32B Thinking, GPT-5.3, DeepSeek-V3.1.