Microsoft
Microsoft develops the Phi small-model family alongside the broader Azure AI stack, focusing on efficient on-device and edge inference.
8 models from Microsoft on Railwail
Access every Microsoft model through Railwail's OpenAI-compatible API.
8 models available
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.
HRNet Pose
Microsoft HRNet high-resolution pose-estimation backbone. Parallel multi-resolution streams yield strong accuracy on COCO keypoint benchmarks.
LayoutLMv3
Microsoft LayoutLMv3 multimodal document model. Unified text/image masking pretraining for form understanding, receipts and document QA.
Microsoft Phi-3.5 MoE Instruct
Mixture-of-experts Phi-3.5: 42B total / 6.6B active params. 128k context, multilingual.
Phi-3.5 Vision
Microsoft Phi-3.5 Vision Instruct. Small (4.2B) multimodal model with strong document, OCR and multi-image reasoning at low cost.
TrOCR Large
Microsoft TrOCR large transformer-based OCR. End-to-end visual encoder plus text decoder, trained on synthetic and printed real-world data.
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.