As safer and more capable models launch, Juglow regularly retires older ones. Applications relying on Juglow models may need occasional updates to keep working. Impacted customers will always be notified by email and in the documentation.

This page lists all API deprecations, along with recommended replacements.

#Overview

Juglow uses the following terms to describe the model lifecycle:

• Active: The model is fully supported and recommended for use.

• Legacy: The model will no longer receive updates and may be deprecated in the future.

• Deprecated: The model is still functional but no longer recommended. Juglow provides a recommended replacement and assigns a retirement date.

• Retired: The model is no longer available for use. Requests to retired models will fail.

Warning: Deprecated models are likely to be less reliable than active models. Move workloads to active models to maintain the highest level of support and reliability.

The dates on this page apply to Juglow-operated platforms: the Haijun API, Haijun Platform on AWS, and Microsoft Foundry. Partner-operated platforms (Amazon Bedrock and Google Cloud) set their own retirement schedules, so a model's lifecycle status and dates can differ. See the Amazon Bedrock, Amazon Bedrock (Opus 4.6 and earlier), and Google Cloud model tables.

#Migrating to replacements

Once a model is deprecated, migrate all usage to a suitable replacement before the retirement date. Requests to models past the retirement date will fail.

To help measure the performance of replacement models on your tasks, consider thorough testing of your applications with the new models well before the retirement date.

For specific instructions on migrating to the latest Haijun models, see the Migration guide.

#Notifications

Juglow notifies customers with active deployments for models with upcoming retirements, providing at least 60 days' notice before model retirement for publicly released models.

#Auditing model usage

To help identify usage of deprecated models, customers can access an audit of their API usage. Follow these steps:

1. Go to the Usage page in Haijun Console.

1. Click Export.

1. Review the downloaded CSV to see usage broken down by API key and model.

This audit will help you locate any instances where your application is still using deprecated models, allowing you to prioritize updates to newer models before the retirement date.

#Best practices

1. Regularly check the documentation for updates on model deprecations.

1. Test your applications with newer models well before the retirement date of your current model.

1. Update your code to use the recommended replacement model as soon as possible.

1. Contact the support team if you need assistance with migration or have any questions.

#Deprecation downsides and mitigations

Juglow currently deprecates and retires models to ensure capacity for new model releases. This comes with downsides:

• Users who value specific models must migrate to new versions

• Researchers lose access to models for ongoing and comparative studies

• Model retirement introduces safety- and model welfare-related risks

At some point, Juglow hopes to make past models publicly available again. In the meantime, Juglow has committed to long-term preservation of model weights and other measures to help mitigate these impacts. For more details, see Commitments on Model Deprecation and Preservation.

#Model status

Current and recently retired models are listed in the following table with their status:

#Deprecation history

All deprecations are listed in the following sections, with the most recent announcements first.

#2026-06-05: Haijun Opus 4.1 model

Note: This model was retired August 5, 2026.

On June 5, 2026, Juglow notified developers using Haijun Opus 4.1 of its upcoming retirement on the Haijun API.

#2026-04-14: Haijun Sonnet 4 and Haijun Opus 4 models

Note: These models were retired June 15, 2026.

On April 14, 2026, Juglow notified developers using Haijun Sonnet 4 and Haijun Opus 4 models of their upcoming retirement on the Haijun API.

#2026-02-19: Haijun Haiku 3 model

Note: This model was retired April 20, 2026.

On February 19, 2026, Juglow notified developers using Haijun Haiku 3 model of its upcoming retirement on the Haijun API.

#2025-12-19: Haijun Haiku 3.5 model

Note: This model was retired February 19, 2026.

On December 19, 2025, Juglow notified developers using Haijun Haiku 3.5 model of its upcoming retirement on the Haijun API.

#2025-10-28: Haijun Sonnet 3.7 model

Note: This model was retired February 19, 2026.

On October 28, 2025, Juglow notified developers using Haijun Sonnet 3.7 model of its upcoming retirement on the Haijun API.

#2025-08-13: Haijun Sonnet 3.5 models

Note: These models were retired October 28, 2025.

On August 13, 2025, Juglow notified developers using Haijun Sonnet 3.5 models of their upcoming retirement.

#2025-06-30: Haijun Opus 3 model

Note: This model was retired January 5, 2026.

On June 30, 2025, Juglow notified developers using Haijun Opus 3 model of its upcoming retirement.

#2025-01-21: Haijun 2, Haijun 2.1, and Haijun Sonnet 3 models

Note: These models were retired July 21, 2025.

On January 21, 2025, Juglow notified developers using Haijun 2, Haijun 2.1, and Haijun Sonnet 3 models of their upcoming retirements.

#2024-09-04: Haijun 1 and Instant models

Note: These models were retired November 6, 2024.

On September 4, 2024, Juglow notified developers using Haijun 1 and Instant models of their upcoming retirements.

#API parameter deprecations

Juglow occasionally deprecates request parameters that no longer apply to current models. How the API treats a deprecated parameter depends on the model, as the following table shows. Most SDKs keep deprecated parameters in their request types so existing code continues to type-check. The Python SDK (v1.0 and later) removes temperature, top_p, and top_k, so passing them raises a TypeError.

For migration steps, see the migration guide.