Components

• Managed hosting Operational
• Model serving Operational
• Monitoring & dashboards Operational
• Support desk Operational

Model changelog

• 1 de jun. de 2026 Added Llama 3.3 70B to the supported model catalog.
• 18 de mai. de 2026 Faster inference with updated vLLM and INT4 quantization presets.
• 2 de mai. de 2026 New governance dashboard: per-team token quotas and alerts.
• 20 de abr. de 2026 DeepSeek R1 and Qwen 2.5 added; improved RAG citation accuracy.