Release Changelog
July 30th, 2025
-
Version 4.0
-
Compass API
- Claude Sonnet 4 (Preview): A reasoning model with improved performance—especially in coding, making it ideal for a wide range of AI tasks, from assistants to large-scale operations. Currently, available to the requested customers.
-
Cohere Command R (Preview): An advanced AI model built to understand and respond in natural, human-like conversations, and is good at handling long and complex discussions. Currently, available to the requested customers.
-
Compass Portal
- Department Management: Users can now create and manage departments directly from their profiles. Within each department, users can create projects and view assigned resources and API keys on the project details page.
-
API Key Management Enhancement: Filtering option in the API Keys section is now available, which simplifies the management of a large volume of Keys. You can filter the API keys by department, project, and environment for quicker access.
-
Compass Portal URL Change: Access the new Compass portal at https://compass.core42.ai. The legacy interface is retired.
-
June 19, 2025
-
Version 3.7
-
Compass Portal
-
Compass is excited to announce that a new version of the Compass platform is now live! Users can explore and preview new features. Dive in to experience the refreshed user interface and discover upcoming functionalities.
-
-
May 31, 2025
-
Version 3.5
-
Compass API
-
GPT Image 1: Compass introduces the GPT Image 1 model, an image generation and natively multimodal that accepts text and image inputs and produces image outputs.
-
o3: Compass introduces the o3, a versatile and robust model that sets a new benchmark for math, science, coding, and visual reasoning. This model excels in technical writing and instruction-following and is capable of solving complex multi-step problems that involve text, code, and image analysis.
-
-
May 11, 2025
-
Version 3.4
-
Compass API
-
o3-mini: Compass introduces o3-mini, the latest compact reasoning model, offering advanced intelligence including essential developer capabilities such as structured outputs, and function calling.
-
o1: Compass introduces the o1 model, designed for complex reasoning tasks, and processing information in a multi-step manner to handle intricate prompts. Its architecture allows for multimodal inputs, enhancing its ability to understand text and images, resulting in coherent text output.
-
Model Deprecation: The gpt-4o-realtime-preview-2024-10-01 model has been deprecated and is no longer available. Suggested replacement: gpt-4o-realtime-preview (version gpt-4o-realtime-preview-2024-12-17).
-
-
Apr 29, 2025
-
Version 3.3
-
Compass API
-
GPT-4.1 (Preview): Compass introduces GPT-4.1, a multimodal model for complex tasks and well-suited for problem-solving across domains. It offers increased efficiency for faster processing and a streamlined user experience.
-
-
Apr 09, 2025
-
Version 3.2.4
-
Compass API
-
GPT-4o Audio (Preview): Compass introduces GPT-4o Audio model that provides real-time, natural voice interactions with improved speed, emotion, and responsiveness for a seamless conversational AI experience.
-
-
Feb 02nd, 2025
-
Version 3.1
-
Compass Portal
-
Batch Jobs Dashboard: We have released a new dashboard that offers an intuitive interface, allowing users to create and manage batch jobs with just a few clicks.
-
Set Spend Limit for Batch Jobs: Users can set separate daily and monthly spend limits for online and batch processing on supported Pay-as-You-Go models.
-
-
Compass API
-
Llama 3.3 70B (Preview): We have featured the latest version of the Llama model, Llama 3.3 70B. This enhanced, high-performance model is both cost-effective and versatile, supporting a wide range of use cases. Now available via the Compass API.
-
Batch Processing: Now supports GPT-4o mini.
-
Web Search: Now supports Mistral 7B, and Mixtral 8x7B.
-
-
Dec 29th, 2024
-
Version 3.0
-
Compass API
-
Realtime model (Paid Preview) : Compass API now supports the Realtime model, enabling fast speech-to-speech experiences in applications.
-
Batch Processing: The Compass API introduces Batch processing capabilities, supporting asynchronous job processing with GPT-4o.
-
-
Compass Chat
-
Attachment upload: Compass chat now lets you attach documents and images through the chat interface and talk to your data.
-
-
Dec 03rd, 2024
-
Version 2.6
-
Compass Portal
-
Budget Limits for PYG-Based Models: Users can now set resource spend limits in USD for daily, monthly, or both, enabling better cost management.
-
Quota Limits for TPM-Based Models: Distribute quota across TPM-based models for enhanced capacity management.
-
Design changes for the Purchase Management and Monitoring: We have streamlined the design for a better user experience.
-
-
Compass API
-
DALL·E 3: Introducing DALL·E, capable of generating images based on prompts. Now available via the Compass API.
-
Web Search API Add-On: Enable web search results with Compass API, leveraging internet knowledge base. Supports GPT-4o, GPT-4o mini, and Llama 3 70B models.
-
New API Authentication Method: API requests now support Authorization: Bearer COMPASS_API_KEY format, ensuring compatibility with OpenAI standards.
-
-
Oct 28th, 2024
-
Version 2.5
-
Compass Portal
-
Support for Multiple Purchases of the Same Model: Users can now purchase the same model multiple times for different use cases.
-
Usage Report Enhancements: Monitor detailed usage statistics per key, customise reporting periods and granularity for deeper insights, and export reports in CSV format for offline analysis and sharing.
-
-
Oct 14th, 2024
-
Version 2.4
-
Compass API
-
Token-Based Pricing: We are excited to announce a new Token-based pricing for an on-demand usage, with integrated monitoring functionalities via the Compass portal.
-
Model Removal: gpt-4-32k as a model is no longer available through Compass.
-
-
Sep 22nd, 2024
-
Version 2.3
-
Compass API
-
GPT-4o Enhancement with Vision Capabilities: Users can now leverage the image-to-text function via the Compass API, enhancing the model's versatility.
-
GPT-4o mini: Introducing one of the most advanced models in the small models category from OpenAI, supporting text inputs and generating text outputs. Now available via the Compass API.
-
Enhancements and Fixes: Various improvements have been made to provide a better user experience.
-
-
Sep 02nd, 2024
-
Version 2.2
-
Compass API
-
Completely Revamped Portal: Enhanced navigation and feature access through the newly designed Compass portal. New capabilities to use, monitor and analyse usage within Compass, providing valuable insights for customers.
-
Stable Diffusion (Preview): Stable Diffusion is a text-to-image model that features great performance in image quality, typography, complex prompt understanding, and resource efficiency, now available via the Compass API.
-
Mixtral 8x7B (Preview): Explore the Mixtral 8x7B for advanced text generation functionalities via the Compass API. Mixtral is a high-quality sparse mixture of experts model (SMoE) with open weights.
-
-
Compass Chat Enterprise
-
Mobile Clients for Android & iOS: The native clients for Android and iOS devices are now available in app stores, providing users with a seamless chat experience on their iPhones.
Google Play: Link
Apple App Store: Link -
RAG (Preview): Launch of Retrieval-Augmented Generation (RAG), with integrations to Confluence and Azure Blob storage.
-
Chat History: A more streamlined interface by unifying the Work and Web search history.
-
Design Enhancements: An improved interface with better readability and user experience.
-
-
Aug 09th, 2024
-
Version 2.1.1
-
Compass API
-
Azure AI Search: Compass now supports the Azure AI Search API, allowing developers to create rich search experiences and generative AI applications, combining LLMs with enterprise data.
-
-
Jul 31st, 2024
-
Version 2.1
-
Compass API
-
Embedding 3 Large: Unlock one of the most capable embedding models from OpenAI with text-embedding-3-large.
-
Mistral 7B (Preview): Explore new possibilities with the mistral-7b model. The first dense model released by Mistral AI, perfect for experimentation, customization, and quick iteration.
-
Llama 3 70B (Preview): Take advantage of the llama3-70B model, a highly performant, cost-effective model that enables diverse use cases.
-
Function Calling Support: Describe functions in an API call and have the model generate JSON objects for function arguments, enabling intelligent function handling in your code. Now available on gpt-4o and gpt-4-32k.
-
Enhanced Performance: Routine performance improvements to make the Compass experience more seamless.
-
Model Removals: llama3-8b and text-embedding-ada-002 are no longer available and have been replaced with more powerful and recent models.
-
-
Compass Chat Enterprise
-
GPT-4o: Leverage the latest and most robust capabilities of gpt-4o in your chat interactions.
-
Web Search (Preview): Enable web search functionality for a more comprehensive chat experience.
-
Android Client (Preview): Our Android-based app makes it easy for you to experience Compass Chat on the go.
-
-
Jun 28th, 2024
-
Version 2.0
-
GPT-4o API: Explore and utilize the powerful text capabilities of OpenAI GPT-4o with this release.
-
Llama 3 API (Preview): Take advantage of Llama 3’s chat completion capabilities with our release.
-
Compass Chat Enterprise : Experience the future of chat with Compass Chat, designed to make your interactions smarter, more engaging, and incredibly convenient.
-
Jun 09th, 2024
-
Version 1.5
-
Speech to Text Capabilities with Whisper model: Incorporate speech to text transcript and translation functionality with Whisper APIs.
-
Email Quota Alerts: Stay informed about quota usage with automated email notifications.
-
Enhanced API Response: Better readability of API headers.
-
Improved User Documentation: Updates to APIs and Langchain documentation for optimal utilization.
-
Updated Legal Framework: Access the User Terms and Conditions and transparent notice for a clear understanding of our service agreements.
-
Apr 19th, 2024
-
Version 1.4
-
Enhanced Langchain Integration: Experience smoother interaction between Compass API and Langchain.
-
Updated Gateway Links: We've updated all gateway domain links.
-
Performance Boost & Bug Squashing: Enjoy a faster and more stable experience thanks to performance optimizations and bug fixes.
-
Jais Arabic LLM Support (Preview): We now offer compatibility with the Jais Arabic Large Language Model.
-
OpenAI Embeddings Integration: Enhance your workflows with the ability to leverage OpenAI Embeddings ada model.
-
Azure OpenAI API Compatibility: Our system now seamlessly integrates with Azure's OpenAI API calling methods.
-
Jan 25th, 2024
-
Version 1.3
-
Enhanced OpenAI Compatibility
-
Jan 12th, 2024
-
Version 1.2
-
New FAQ page
-
New Changelog page
-
Dec 15th, 2023
-
Version 1.1
-
New UI theme for the Developer’s Portal
-
Traffic throttling based on TPM
-
Usage monitoring
-
Dec 05th, 2023
-
Version 1.0
-
Interference API with GPT-4 Compatibility
-
Usage monitoring
-
Enhanced Developer Portal
-