Learn by Building
Move beyond chat: build API-powered tools for coursework, coding, experiments, and course projects.
LLM API Gateway
Build, Learn, Explore with LLM APIs.
SoCLaaS provides free access to powerful, OpenAI-compatible LLM APIs for teaching, learning, experiments, prototypes, and the next idea you want to bring to life—from first prompt to real-world impact.
SoCLaaS is a service of the School of Computing (SoC) at the National University of Singapore (NUS).
Experiment Without Friction
Compare approaches, improve prompts, and learn through the trial and error that turns curiosity into capability.
Create With Confidence
Try ideas, refine prompts, and learn from failures with room to iterate—without every experiment becoming a cost decision.
Integrate With Your Tools
Connect third-party web chat, Codex, OpenClaw, and other agentic tools to SoCLaaS through its OpenAI-compatible API.
OpenAI-Compatible API
One API. More Ways to Build.
From a first prompt to an agent workflow, searchable knowledge base, or lecture transcript—build on one familiar API surface.
Chat Completions
POST /v1/chat/completionsTurn questions, instructions, and ideas into useful conversations.
Responses
POST /v1/responsesBuild tool-using workflows and agent experiences with a familiar API shape.
Embeddings
POST /v1/embeddingsMake documents, notes, and knowledge bases meaningfully searchable.
Audio Transcription
POST /v1/audio/transcriptionsTurn interviews, lectures, and recordings into text.
Model Capabilities
Language and Reasoning
Draft, explain, analyse, summarise, translate, and work through questions in natural language.
Code and Agent Work
Write, review, and debug code; use tools; and carry multi-step development tasks forward.
Images, Documents, and Video
Interpret visual information in images, diagrams, charts, documents, and video—then answer questions about it.
Document Reading and OCR
Read text from images, understand document structure, and extract key details from complex material.
Long-Context Research
Work across lengthy papers, technical documentation, codebases, and other large bodies of material.
Retrieval and Transcription
Create multilingual embeddings for semantic search, and turn interviews, lectures, and recordings into text.
Different selected models support different capabilities; use the model catalogue to see what is available to your API key.