Microsoft
Microsoft develops the Phi small-model family alongside the broader Azure AI stack, focusing on efficient on-device and edge inference.
5 models from Microsoft on Railwail
Access every Microsoft model through Railwail's OpenAI-compatible API.
5 models available
BiomedBERT (PubMedBERT abstract)
Microsoft BiomedBERT (formerly PubMedBERT) pretrained from scratch on PubMed abstracts with a domain-specific vocabulary, rather than adapting a general model. As a feature extractor it gives 768-dim biomedical embeddings and set the original state of the art on the BLURB biomedical NLP benchmark.
Edge TTS
Microsoft Edge neural voices accessed via the open-source edge-tts wrapper. 400+ voices across 100+ locales, suitable for batch generation.
Florence-2 Large
Microsoft Florence-2 Large. Unified prompt-based vision foundation model for captioning, detection, segmentation and OCR with a single 770M-param backbone.
Florence-2 Segmentation
Microsoft Florence-2 unified vision model with referring expression segmentation. Text-prompted region and mask generation in one model.
Multilingual E5 Large
Microsoft E5 multilingual embedding model with 560M parameters, initialized from XLM-RoBERTa-large and trained with weakly supervised contrastive learning. Covers around 100 languages and returns 1024-dim vectors. It expects query: and passage: prefixes on inputs and is a popular open model for multilingual semantic search.
Frequently asked questions
How is Microsoft pricing handled on Railwail?
Are there rate limits when using Microsoft via Railwail?
Which regions does Microsoft support through Railwail?
Is there a sandbox or free tier to test Microsoft models?
Start building with Microsoft today
Free credits on sign-up. No credit card required. Access Microsoft and 27+ other providers through a single API.