Models

Our model services provide easy access to state-of-the-art models through a unified API interface to help accelerate your AI development in government. Beyond having comprehensive governance controls to ensure compliance and security requirements, we also look at optimising throughput performance while optimising for cost efficiency.

Key Features

  • Seamless Model Access: OpenAI-compatible interface for quick integration and model swapping
  • Centralised Management: Team & key level configuration controls to ensure effective cost management and appropriate developer access.
  • Cost Efficiency: Centralised demand aggregation for economies of scale
  • Compliance & Security: Safety guardrails (Sentinel) and adherence with IM8 and GenAI circular requirements

Use Cases

  • Conversational AI and chatbots
  • Automated content creation
  • Code generation and review
  • Knowledge extraction and summarization
Interested?

Sign in now to get your API key and start integrating today.

Featured models

OpenAI

GPT-5.4: Intelligent model with ability to decide between fast chat mode or complex reasoning.

Others: GPT-5.4-pro, GPT-5.3-codex, o4-mini, text-embedding-3-small

Claude

Sonnet 4.6: Combines superior reasoning and coding abilities with efficient everyday performance.

Others: Claude Opus 4.6, Claude Haiku 4.5

Google Gemini

Gemini 2.5 Pro: Advanced thinking model with large context window of 1 million tokens and strong multimodal capability.

Others: Gemini 2.5 Flash, Gemini 2.5 Flash-Lite

Cohere

Cohere Embed Multilingual: Multilingual embedding model supporting 100+ languages.

Others: Cohere Embed English

View all available models

Models

Models provides seamless access to powerful Cloud Service Providers (CSPs) and self-hosted language models for fast, scalable text generation and natural language understanding. It simplifies integration by managing API keys, handling dynamic load balancing, and ensuring compliance with data standards. With easy access to multiple LLMs and tools for monitoring usage and billing, Models streamlines the deployment of AI-enhanced solutions across applications.

  • To view the models currently offered, please refer to the Models Offered section.
  • For details on how to use Models, please refer to the API Reference section.

Do note that new users will be onboarded to Models. Existing users of LLM-as-a-Service (LLMaaS) may refer to the relevant documentation under LLM-as-a-Service (deprecating) for more information.

Get Access to Models

To gain access to Models, please submit the "Sign up now" form and we will reach out to better understand your use case and requirements. After reviewing your form, we will reach out to discuss your use case further before providing you with an API key via email. This process ensures we can meet your needs effectively.

For the free trial period, the budget is typically 10 USD / month and the rate limit is 20 requests / min.

Feel free to contact us if you require a higher budget or increased rate limits.