Pricing
Pricing Plans Comparison
| Features | Description | Basic | Standard | Professional | Enterprise |
|---|---|---|---|---|---|
| Price (Monthly) | Cost of the plan per month. | 49 € | 199 € | 499 € | Custom Pricing |
| Search Queries + Updates per Month | Combined limits for search queries and document updates per month. | 100k | 200k | 600k | Flexible |
| Document Count Limit | Maximum number of documents stored at any time. | Up to 10k | Up to 100k | Up to 1M | Flexible |
| Indices Included | Number of separate indices (collections of data). | 1 | Up to 5 | Up to 10 | Flexible |
| Index Size Limit | Total storage space for all indices combined. | Up to 100 MB | Up to 1 GB | Up to 5 GB | Flexible |
| Tenant/Users | Number of Tenant/Users included in the plan. | 1 Tenant / 1 User | 1 Tenant / 3 Users | 1 Tenant / 5 Users | Flexible |
| Historical Backup Indices¹ | Number of historical snapshots of indices available for recovery or auditing. | 0 | 1 | 3 | Customizable |
| Feeding Updates Frequency | Frequency of data ingestion and updates. | Daily | Hourly | Real-time | Real-time |
| Analytics Dashboard | Access to reporting and search analytics tools. | Basic | Advanced | Real-time | Custom/Editable Dashboards |
| Analytics Metrics Retention | Minimum retention period for analytics metrics. | 30 days | 60 days | 90 days | 90+ days |
| Support | Type of technical assistance offered. | Email Only | Email Only | Priority Support | 24/7 Priority Hotline |
| Personal Contact | Direct access to a dedicated account manager. | ❌ | ❌ | ✅ | ✅ |
| Premier Support³ | Access to dedicated experts, fast issue resolution, and proactive monitoring. | ❌ | ❌ | ❌ | ✅ |
| Onboarding | Assistance during initial setup and configuration. | ❌ | ❌ | ✅ | ✅ |
| API Access | Ability to integrate advanced API access. | ❌ | ✅ | ✅ | ✅ |
| Dedicated Infrastructure² | Ensures high performance and security by providing exclusive infrastructure. | ❌ | ❌ | AWS, GCP, Azure² | AWS, GCP, Azure, On-premise² |
| Audit Log | Provides a detailed record of all system activities for compliance and security. | ❌ | ❌ | ❌ | ✅ |
| Service Level Agreement (SLA) | Uptime guarantee. | 99% | 99.5% | 99.97% | 99.99% |
Note: Additional fees may apply when usage exceeds plan limits. Please refer to the Additional Features and Services table for details.
Classic Search Features
Quasiris Search Cloud offers a comprehensive suite of classic search functionalities, providing a user-friendly interface built atop a headless API. While we deliver robust traditional search features, our primary focus is on automation, artificial intelligence, and enhancing usability to offer an exceptional search experience.
AI-Powered Features⁴⁵
| AI Feature | Description | Basic | Standard | Professional | Enterprise |
|---|---|---|---|---|---|
| Natural Language Understanding | Interprets and responds to complex user queries using advanced NLP techniques. | ❌ | ❌ | ✅ | ✅ |
| Predictive Search | Suggests query completions and recommendations as users type. | ❌ | ✅ | ✅ | ✅ |
| Semantic Search | Matches the intent behind user queries with relevant results, even without exact keyword matches. | ❌ | ❌ | ✅ | ✅ |
| Smart Snippets | Automatically generates concise, relevant answers to user queries. | ❌ | ❌ | ❌ | ✅ |
| Question Answering | Delivers direct answers to user questions using AI-powered natural language understanding. | ❌ | ❌ | ✅ | ✅ |
| Dynamic Faceting | Automatically generates relevant filters based on user behavior and query context. | ❌ | ✅ | ✅ | ✅ |
| Automatic Re-ranking | Uses AI to re-order search results based on relevance, engagement, and contextual signals. | ❌ | ❌ | ✅ | ✅ |
| Federated Search | Enables searching across multiple data sources and repositories simultaneously. | Coming Soon | Coming Soon | Coming Soon | ✅ |
| Intent Detection | Determines the user’s intent behind queries to deliver more relevant results. | ❌ | ❌ | ✅ | ✅ |
| Hybrid Search | Combines multiple search methodologies for optimal accuracy and relevance. | ❌ | ❌ | ✅ | ✅ |
| Smart Classifier | Automatically classifies and categorizes content or documents using machine learning models. | ❌ | ❌ | ✅ | ✅ |
| Intelligent Insights | Extracts actionable insights from search data to improve decision-making and user experience. | ❌ | ❌ | ✅ | ✅ |
| Model Configurability | Customize and fine-tune AI models to align with specific business goals and domains. | ❌ | ❌ | ✅ | ✅ |
| Personalization | Adapts search results based on individual user behavior and preferences. | ❌ | ❌ | ✅ | ✅ |
| Guided Selling | Provides personalized product recommendations based on user needs and preferences. | ❌ | ❌ | ✅ | ✅ |
| Conversational AI | Supports interactive, conversational interfaces for search, such as chatbots and virtual assistants. | ❌ | ❌ | ✅ | ✅ |
| Advanced AI Model Training | Provides tools for building, testing, and deploying custom AI models. | ❌ | ❌ | ✅ | ✅ |
| Multilingual Search | Offers accurate search results in multiple languages, supporting global user bases. | ❌ | ❌ | ✅ | ✅ |
| Image Search | Enables searching using images and visual content analysis. | ❌ | ❌ | ✅ | ✅ |
| In-Product Search | Enables fast and accurate search within your application or website. | Coming Soon | Coming Soon | Coming Soon | Coming Soon |
AI Plugins⁴⁵
| AI Plugin | Description | Basic | Standard | Professional | Enterprise |
|---|---|---|---|---|---|
| OpenAI Integration | Leverage OpenAI’s advanced language models for enhanced AI capabilities. | ❌ | ❌ | ✅ | ✅ |
| AWS Bedrock Integration | Utilize AWS Bedrock services for scalable AI applications. | ❌ | ❌ | ✅ | ✅ |
| Google Vertex AI Integration | Access Google’s Vertex AI platform for powerful machine learning models and tools. | ❌ | ❌ | ✅ | ✅ |
| Mistral AI Integration | Integrate with Mistral AI for advanced data analysis and insights. | ❌ | ❌ | ✅ | ✅ |
| Anthropic Claude Integration | Incorporate Anthropic’s Claude for sophisticated conversational AI capabilities. | ❌ | ❌ | ✅ | ✅ |
| Custom AI Plugin Support | Incorporate Anthropic’s Claude for sophisticated conversational AI capabilities. | ❌ | ❌ | ❌ | ✅ |
Additional Features and Services
| Feature | Description | Price |
|---|---|---|
| Extra Indices | Add more indices beyond the plan’s limit. | 49 €/month per index |
| Additional Search Queries or Updates | Increase the combined limit of search queries or updates beyond the plan’s allowance. | 0.30 € per 1,000 entries |
| Document Count Limit | Exceeding the document count limit incurs an additional fee. | 0.25 € per 1,000 documents |
| Index Size Overage | Exceeding the index size limit incurs an additional fee. | 499 €/GB |
| Custom Integrations | Develop bespoke integrations for specific business requirements. | Custom Pricing |
| Consultation Services | Access to expert guidance on AI models and search optimization. | Custom Pricing |
Footnotes
- Historical Backup Indices are included in the plan at no additional cost, allowing access to snapshots for recovery and auditing.
- Dedicated Infrastructure: Starting with the Professional package, dedicated infrastructure is available with limitations. Contact sales for details.
- Premier Support: Consultation Services can be booked separately as listed in Additional Features and Services.
- Feature Availability: Availability depends on domain and use case. In regular scenarios, these features start with the Professional or Enterprise package.Some features use or require LLM (Large Language Models) integration, which incurs an additional fee. Using your own models can help reduce costs.Please contact sales for more information.
- Model Integration:Enterprise/Professional Customers: New models can be added upon request to meet specific requirements. Additional models are available on request, subject to evaluation and use case.
Supported Models for Cloud Integration
| Model Name | Description | Availability |
|---|---|---|
| Amazon Titan Text Embeddings V2 | Amazon’s current text embedding model optimized for semantic search, retrieval, and RAG applications. | ✅ |
| Amazon Nova Multimodal Embeddings | Amazon’s multimodal embedding model for semantic retrieval across text, images, audio, and video. | ✅ |
| Cohere Embed v4.0 | Cohere’s advanced multilingual and multimodal embedding model for text, images, and mixed-content documents. | ✅ |
| OpenAI text-embedding-3-small | OpenAI’s efficient embedding model optimized for cost-effective semantic search and retrieval. | ✅ |
| OpenAI text-embedding-3-large | OpenAI’s high-performance embedding model optimized for multilingual semantic search and retrieval. | ✅ |
| Vertex AI gemini-embedding-001 | Google’s high-performance embedding model for English, multilingual, and code retrieval tasks. | ✅ |
| Voyage AI voyage-4-large | Voyage AI’s highest-quality general-purpose and multilingual embedding model for advanced retrieval. | ✅ |
| Voyage AI voyage-4 | Voyage AI’s general-purpose embedding model optimized for multilingual semantic search and retrieval. | ✅ |
| Voyage AI voyage-4-lite | Voyage AI’s efficient embedding model optimized for low latency and cost-effective large-scale retrieval. | ✅ |
| Voyage AI voyage-code-4 | Voyage AI’s specialized embedding model optimized for source code retrieval and AI coding applications. | ✅ |
| Qwen3-Embedding-8B | High-performance open-weight multilingual embedding model optimized for text, code, and cross-lingual retrieval. | ✅ |
| Qwen3-Embedding-4B | Powerful open-weight multilingual embedding model balancing retrieval quality and computational efficiency. | ✅ |
| Qwen3-Embedding-0.6B | Compact open-weight multilingual embedding model optimized for efficient semantic search and retrieval. | ✅ |
| Jina Embeddings v5 Text Small | Jina AI’s fifth-generation multilingual text embedding model optimized for retrieval, matching, clustering, and classification. | ✅ |
| Jina Embeddings v5 Text Nano | Lightweight multilingual embedding model from Jina AI optimized for efficient and resource-conscious deployments. | ✅ |
| Jina Embeddings v5 Omni Small | Multimodal embedding model supporting text, images, audio, video, and documents in a unified semantic vector space. | ✅ |
| Jina Embeddings v5 Omni Nano | Compact multimodal embedding model for semantic retrieval across text, images, audio, video, and documents. | ✅ |
Note: This list changes rapidly and may be outdated. Please contact us for the most current information.