Mercury 2
VerifiedMercury 2 handles extended text contexts with precision.
About Mercury 2
Mercury 2 was developed as a closed-weight system by Inception, with no public parameter count disclosed. Its 128000-token context window forms the core architectural feature, enabling retention of lengthy input sequences without truncation. This design prioritizes coherence across extended documents or dialogues.
Strengths center on maintaining context fidelity in text-based interactions. Typical usage includes analysis of long-form content, multi-turn conversations, and summarization of detailed source material where preserving distant details matters.
Capabilities
How Mercury 2 compares
Mercury 2 (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Mercury 2 ranks #29 of 66
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long Document Analysis
Mercury 2 processes entire documents up to 128000 tokens for deep reasoning tasks such as extracting insights from research papers or reports.
Extended Multi-Turn Dialogues
It maintains coherence across lengthy conversations while following complex instructions over many exchanges.
Large-Scale Text Summarization
The model generates concise summaries and performs document-level reasoning on extensive inputs like books or datasets.
Strengths & limitations
Strengths
- +Strong support for large context windows
- +Effective at maintaining coherence over long inputs
- +Suitable for text-only workflows
Limitations
- –Text modality only with no vision or audio support
- –No demonstrated multimodal integration
- –Performance details beyond context length remain unspecified
Pricing by provider
Live per-provider pricing & uptime, routed via OpenRouter. Prices are USD per 1M tokens.
| Provider | Input /1M | Output /1M | Context | Uptime |
|---|---|---|---|---|
| Inception | $0.25 | $0.75 | 128K | 100.0% |
Cost calculator
Estimate what Mercury 2 would cost for your usage.
Based on Mercury 2's $0.25/1M input · $0.75/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "inception/mercury-2",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: inception/mercury-2
Editor's verdict
Mercury 2 is Inception's proprietary language models with a 128K-token context window.
At $0.75 per 1M output tokens, it is very cost-efficient for its class, served by 1 provider.
It is available through Inception's API and aggregators like OpenRouter.
Best suited to strong support for large context windows and effective at maintaining coherence over long inputs.
Frequently asked questions
Mercury 2 supports a context window of 128000 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Similar models
Other language models worth comparing.