FlagshipInception

Mercury

Mercury is Inception's flagship text-only model with a 128K token context window, designed for complex language understanding and generation tasks.

Context 128K
Tier Flagship
Input from
$0.250 / 1M tokens
across 1 provider

API Pricing

ProviderInput / 1MOutput / 1MUpdated
$0.250$0.7504/14/2026

Prices updated daily. Last check: 4/14/2026

Model Details

General

Creator
Inception
Family
Mercury
Tier
Flagship
Context Window
128K
Modalities
Text

Capabilities

Tool Calling
No
Open Source
No

Strengths & Limitations

  • 128K token context window enables processing of lengthy documents and extended conversations
  • Flagship-tier model provides advanced language understanding capabilities
  • Text-focused architecture optimizes performance for language-specific tasks
  • Suitable for complex document analysis and content generation workflows
  • Large context capacity reduces need for document chunking in many applications
  • No multimodal support - text input and output only
  • Tool calling functionality not available
  • Proprietary model with no open source availability
  • Context window smaller than some competing flagship models
  • Limited to text-based use cases compared to multimodal alternatives

Key Features

128,000 token context window
Text input and output processing
Flagship-tier language understanding
Document analysis capabilities
Extended conversation memory
Complex text generation
Multi-document processing within context limit

About Mercury

Mercury is Inception's flagship language model, representing the company's most advanced offering in their Mercury model family. As a proprietary large language model, Mercury focuses exclusively on text-based tasks while delivering high-performance capabilities across various language understanding and generation scenarios. The model features a 128,000 token context window, allowing it to process substantial amounts of text in a single request. Mercury operates as a text-only model, concentrating computational resources on language tasks without multimodal capabilities. The model does not include tool calling functionality, focusing instead on direct text generation and comprehension. Mercury serves users who need sophisticated text processing capabilities for complex documents, content creation, and analysis tasks. Its substantial context window makes it suitable for working with lengthy documents, research papers, and multi-part conversations where maintaining context across extended interactions is important.

Common Use Cases

Mercury is well-suited for applications requiring sophisticated text processing and analysis, particularly where large context windows are valuable. Common use cases include analyzing lengthy research documents, generating comprehensive reports, processing legal or technical documentation, and maintaining context across extended conversations or multi-part queries. The model's flagship-tier capabilities make it appropriate for complex writing tasks, document summarization, and content creation workflows where nuanced language understanding is important. Organizations working with substantial text corpora or requiring detailed analysis of lengthy materials will find Mercury's 128K context window particularly beneficial for maintaining coherence across entire documents without segmentation.

Frequently Asked Questions

How much does Mercury cost per million tokens?

Mercury pricing varies by provider and may include different rates for input and output tokens. Check the pricing table above for current rates across all available providers offering Mercury access.

What is Mercury best used for?

Mercury excels at complex text processing tasks that benefit from its 128K context window, including document analysis, comprehensive report generation, lengthy content creation, and applications requiring sustained context across extended conversations or multi-part documents.

Does Mercury support image input or tool calling?

No, Mercury is a text-only model that focuses exclusively on language tasks. It does not support image input, vision capabilities, or tool calling functionality. Users requiring these features would need to consider multimodal alternatives.