Quick Start
- 1
- 2Use the Microsoft Foundry SDK or REST API to call
jais-30b— see the documentation for request format. - 3
Code Examples
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 Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development. It provides access to over 1,900 models from Microsoft, OpenAI, Anthropic, Mistral, xAI, Meta, DeepSeek, Hugging Face, and more. Foundry unifies agents, models, and tools under a single management grouping with built-in enterprise-readiness capabilities including tracing, monitoring, evaluations, and customizable enterprise setup configurations.
Pricing on Microsoft Foundry
| Type | Price (per 1M) |
|---|---|
| Input tokens | $3.20 |
| Output tokens | $9.71 |
Capabilities
No model capability flags are currently sourced.
About Jais 30B
The Jais 30B is a leading bilingual large language model developed by Core42 and Cerebras Systems, designed for both Arabic and English. Featuring 30 billion parameters, it leverages a transformer-based decoder-only architecture, offering enhanced performance with SwiGLU non-linearity and ALiBi position embeddings. This model excels in text generation, conversational AI, summarization, and translation, capable of handling lengthy contexts with up to 8,192 tokens. Trained on an extensive dataset of 126 billion Arabic tokens, 251 billion English tokens, and 50 billion code tokens, Jais 30B is open-source under the Apache 2.0 license, facilitating community collaboration. Despite its capabilities, it may exhibit biases and is recommended to be used with human oversight.