Skip to content
  • There are no suggestions because the search field is empty.

2026 Changelog

April 13, 2026
Version 4.9.5

Compass API and Portal
GPT-5.4

GPT-5.4 has been onboarded to the Compass platform. This model brings enhanced performance for complex reasoning, coding, and agentic workflows, supporting multimodal inputs and advanced capabilities.

Claude Sonnet 4.6

A mid-tier model delivering a strong balance of speed and intelligence, with major upgrades across coding, agent workflows, long-context reasoning, and computer use capabilities.

Claude Opus 4.6

Anthropic’s most advanced model for complex reasoning, coding, and agentic workflows, designed to deliver top-tier intelligence and planning capabilities for enterprise-scale use cases.

 

April 08, 2026
Version 4.9.4

Compass API and Portal
Mistral Small 3.2

Mistral Small 3.2 has been onboarded to the Compass platform. This is a 24B parameter multimodal model optimized for low-latency, cost-efficient inference, with strong instruction-following and function calling capabilities.

Model Retirement

Mixtral 8x7B has been retired from the Compass platform and is no longer available for use.


 

April 07, 2026
Version 4.9.3

Compass API
Function Calling Support Enabled for Mistral 7B

Function calling capability has been successfully enabled for the Mistral 7B model via Azure VM deployment.

  • Mistral 7B now supports structured function/tool invocation
  • Integrated using Azure VM deployment endpoint
 

April 01, 2026
Version 4.9.1

Compass API

Kimi-K2.5 (Preview)
Multimodal foundation model built for long-context understanding, tool use, and advanced coding or agent-driven workflows.

GLM-5 (Preview)
Flagship foundation model designed for agentic engineering, with strong performance in complex reasoning, coding, and long-range task execution.

Batch Support Extended
Enabled batch processing support for GPT-4.1 and GPT-4.1 mini models. The usage, pricing, and billing are consistently reflected across:

  • Usage Dashboard

  • Subscription billing models

Model Retirement
The DALL·E 3, and Jais30b model have been retired and no longer available on Compass Platform.

Response API model update
Response API has been updated to support additional models, including GPT-5 and GPT-5.1.

 

Mar 05th, 2026
Version 4.9

Compass Portal

Resource Management Updates
A new expiry filter on the Resources Management page allows users to view resources by status (≤30, ≤15, ≤7 days, or Expired). An Expiring Soon alert is now displayed near the page title for improved visibility. Resources expiring within 30 days are clearly highlighted for users in both the list and details views.

Subscription Expiry Notification
Root admins will now receive reminder emails 30, 15, 7, and 1 days before the subscription expires.

Set Up Alerts to Receive Notifications
Added a new ALERTS tab under User Profile > Settings, enabling Root Admins to configure notification preferences directly from the portal UI.
Admins can now manage alerts for Model Performance, Utilization, Budget & Spend, Resource Expiry, and Monthly Reports with configurable thresholds.

Compass API

K2 Think V2 Cerebras
The K2 Think Cerebras model has been upgraded to K2 Think V2 Cerebras. The model is deployed and running on the Cerebras in the US region. The existing model is no longer available, and all users must migrate to K2 Think V2  Cerebras.

Model Retirement
The o3 model has been retired. The suggested replacement model is o4-mini.

 
Feb 13th, 2026

Version 4.8

Compass Portal

API Key Limit Increase to 300 per Project
The maximum number of API keys that can be created per project has been increased to 300.

Compass API

GPT-5.2 (Preview)
One of the flagship models for coding and agentic tasks with configurable reasoning support.

GPT-4.1 mini
Optimized model for instruction following and tool calling, offering a 1M-token context window and low-latency responses without a dedicated reasoning step. The model is deployed in the UAE region.

 

Feb 05th, 2026
Version 4.7.2

Compass Portal

UI Update: Compass Login Button
The Compass login page is revamped, and the button previously labeled Continue with Microsoft has been revised to Sign in.

Compass API

Compass Consumption & Usage APIs
Compass now provides secure, programmatic access to detailed consumption and usage data via APIs. This enables customers to build custom dashboards, integrate with internal BI tools, and monitor AI usage without logging into the Compass Portal.

 
Jan 22nd, 2026

Version 4.7.1

Compass API

GPT 5.1 Enhancements
GPT-5.1 is now available in production and in the UAE region.

 

Jan 20th, 2026
Version 4.7

Compass Playground

Enhanced API Key Management
The Playground now displays associated API keys sorted by most recently updated or created. Users without an associated API key will see a guided message explaining how to create and link one. This update improves usability and onboarding for both new and existing users.

Compass Portal

Support Ticket Submission from Compass Portal
Compass users can now submit support tickets directly from the navigation menu within the platform, enabling faster assistance without disrupting their workflow.

Compass API

GPT 5.1 (Preview)
An advanced model with enhanced understanding, reasoning ability, and designed to be more accurate, flexible, and efficient.

Single API Endpoint to Retrieve Model Definitions
Compass now provides a single, standardized API endpoint that allows users to retrieve all available model definitions within the platform.

API Key Visibility Controls
A new field, API Key Visibility, has been added in the Create API Key screen, allowing root admins to manage which department users can view, edit, or regenerate specific API keys rather than granting visibility to all users by default.

GPT-4o Model Routing 
Starting January 20, 2026, the Compass API model routing has been updated to standardize usage on a single GPT-4o version. Requests previously routed to gpt-4o, gpt-4o-2024-11-20, gpt-4o-2024-08-06, will now be routed exclusively to gpt-4o-2024-11-20.

Model Retirement
The GPT-4o model version gpt-4o-2024-08-06 has been retired. All requests sent to this model will now be automatically routed to gpt-4o-2024-11-20.

Model Deprecation and Retirement Guide
To help you plan as models evolve, Compass now includes a dedicated documentation page that clearly communicates model deprecations and retirements. The documentation provides information about the:

  • Models that are already deprecated

  • Models that are scheduled for deprecation

  • Models that are retired or scheduled for retirement

 

Jan 02nd 2026

Version 4.6.6

Compass API

LFM2-8B-A1B
A high-efficiency 8.3B parameter hybrid Mixture-of-Experts (MoE) language model designed for fast, memory-efficient inference on phones, laptops, and embedded systems, with support for both CPU- and GPU-based deployments. The model is deployed on the Core42 cloud in the UAE region.