RHEL AI Models — Pricing & Benchmarks
4 models available · Red Hat
RHEL AI hosts 4 AI models in this catalog. Per-token pricing is not listed for these RHEL AI rows yet; compare context windows, benchmarks, and hosting options instead. LLM Reference lets you compare these models across all 63 providers without switching tabs.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| Granite 20B Code | — | — | 8K | |
| Granite 34B Code | — | — | 8K | |
| Granite 3B Code | — | — | 8K | |
| Granite 8B Code | — | — | 8K |
About RHEL AI
Red Hat OpenShift AI is a comprehensive platform designed for developing, deploying, and managing AI and machine learning workloads across hybrid cloud environments. It integrates essential tools like TensorFlow, PyTorch, and Jupyter, enabling seamless collaboration between data scientists and developers. The platform facilitates rapid model development, operationalizes AI/ML models using Kubernetes, and supports both small-scale experiments and large-scale production models. With advanced security measures and a cloud-native architecture, it offers flexible deployment options as either a managed service or self-managed software. A standout feature of Red Hat OpenShift AI is its support for retrieval-augmented generation (RAG), allowing users to derive AI insights from their own reference documents. The platform enhances model serving with multi-model server capabilities and distributed workloads, utilizing technologies such as KServe and Ray for efficient data processing. It emphasizes community-driven innovation through open-source principles, enabling enterprises to modernize their applications and infrastructure, and ultimately drive productivity and competitive advantage in the AI landscape.
Full provider profile →