Quick Start
- 1
- 2Use the Microsoft Foundry SDK or REST API to call
smaug-72b— see the documentation for request format. - 3You'll be billed $1.00/1M input, $2.00/1M output tokens.
About Microsoft Foundry
Microsoft Foundry offers a comprehensive platform-as-a-service for enterprise AI operations. It provides multiple deployment options including Serverless APIs (pay-as-you-go), Global Standard (shared managed capacity), Provisioned Throughput Units (reserved capacity), batch processing, and bring-your-own model deployments. The platform features a unified control plane for models, agents, tools, and observability. Its Agent Service enables building and deploying AI agents with built-in tracing, monitoring, and governance. Evaluation and monitoring tools assess model performance, safety, and groundedness. Foundry supports seamless upgrades from Azure OpenAI with non-destructive migration, maintaining existing deployments while unlocking multi-provider model access and advanced platform capabilities.
Microsoft Foundry is a unified enterprise AI platform that significantly expands beyond Azure OpenAI. It functions as a multi-provider hosting and deployment platform for LLMs, supporting models from OpenAI, Anthropic, DeepSeek, xAI, Meta, Mistral, NVIDIA, and others. Foundry integrates agent services, evaluation, observability, and governance into a single Azure control plane. Key capabilities include a multi-provider model catalog, Model Router for intelligent prompt routing, Foundry Agent Service for building and deploying AI agents with built-in tracing and monitoring, and enterprise-grade governance with RBAC, compliance, and regional deployments. For broader model catalog including Claude, DeepSeek, Grok, Llama, Mistral, and NVIDIA Nemotron, Foundry is the recommended platform over Azure OpenAI.
Pricing on Microsoft Foundry
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.00 |
| Output tokens | $2.00 |
Capabilities
About Smaug 72B
Smaug 72B is a large language model (LLM) developed by Abacus AI, distinguished as the first open-source model to exceed an average score of 80% on the Hugging Face Open LLM Leaderboard. It excels in various tasks, outperforming even some proprietary models like GPT-3.5 in specific benchmarks. The model is based on the Qwen-72B and fine-tuned using a novel DPO-Positive (DPOP) technique, leveraging datasets such as ARC, HellaSwag, and MetaMath. Its capabilities include question answering, text translation, and poem generation, with notable performance in reasoning and math tasks. Despite its strengths, Smaug 72B faces limitations such as dataset contamination and challenges in complex contextual understanding. Its open-source nature allows for community-based enhancements and it supports a 32k context length for processing longer inputs.