Details
Asset Version: 1.0.0
Last Published: Jun 25, 2026
By: HCL Volt MX Team
The Nebius Adapter allows Volt MX applications to access multiple AI models through a single REST API interface. It supports features such as chat completions, text generation, embeddings, reranking, image generation, usage tracking, and project-level management. The adapter uses OpenAI-compatible API formats, making it easy to integrate AI capabilities into applications with minimal changes while simplifying access to different AI providers through a unified platform.
Requirements
- HCL Volt MX Foundry
Devices
Platforms
Features:
- Multiple Model Access: Access models from OpenAI, Anthropic, Google, and open-source models like Llama and Mistral through one unified API.
- Unified Text Generation & Chat:Generate text, chat responses, summaries, and conversational AI using a single OpenAI-compatible API.
- Smart Model Routing:Automatically select the best model based on cost, speed, or performance needs.
- AI Request Logging & Observability:Track all API requests and responses for debugging, monitoring, and performance analysis.
- Cost Tracking & Usage Analytics:Monitor token usage and costs across all models to manage and optimize spending.
- Caching & Performance Optimization:Reuse repeated responses to reduce latency and lower API costs.
- Failover & Reliability Handling:Automatically retry or switch models if a request fails to ensure reliability.
- OpenAI-Compatible REST API:Integrates easily using standard HTTP requests and JSON formats without major code changes.
- Prompt Testing & Experimentation:Compare prompts across different models to improve output quality.
- Scalable & Developer-Friendly:Build and scale AI applications easily without managing multiple provider APIs separately.
