Deprecations

​

Overview

We regularly update our platform with the latest and most powerful open-source models. This document outlines our model lifecycle policy, including how we handle model upgrades, redirects, and deprecations.

​

Model Lifecycle Policy

To ensure customers get predictable behavior while we maintain a high-quality model catalog, we follow a structured approach to introducing new models, upgrading existing models, and deprecating older versions.

​

Model Upgrades (Redirects)

An upgrade is a model release that is materially the same model lineage with targeted improvements and no fundamental changes to how developers use or reason about it. A model qualifies as an upgrade when one or more of the following are true (and none of the “New Model” criteria apply):

• Same modality and task profile (e.g., instruct → instruct, reasoning → reasoning)
• Same architecture family (e.g., DeepSeek-V3 → DeepSeek-V3-0324)
• Post-training/fine-tuning improvements, bug fixes, safety tuning, or small data refresh
• Behavior is strongly compatible (prompting patterns and evals are similar)
• Pricing change is none or small (≤10% increase)

Outcome: The current endpoint redirects to the upgraded version after a 3-day notice. The old version remains available via Dedicated Endpoints.

​

New Models (No Redirect)

A new model is a release with materially different capabilities, costs, or operating characteristics—such that a silent redirect would be misleading. Any of the following triggers classification as a new model:

• Modality shift (e.g., reasoning-only ↔ instruct/hybrid, text → multimodal)
• Architecture shift (e.g., Qwen3 → Qwen3-Next, Llama 3 → Llama 4)
• Large behavior shift (prompting patterns, output style/verbosity materially different)
• Experimental flag by provider (e.g., DeepSeek-V3-Exp)
• Large price change (>10% increase or pricing structure change)
• Benchmark deltas that meaningfully change task positioning
• Safety policy or system prompt changes that noticeably affect outputs

Outcome: No automatic redirect. We announce the new model and deprecate the old one on a 2-week timeline (both are available during this window). Customers must explicitly switch model IDs.

​

Active Model Redirects

The following models are currently being redirected to newer versions. Requests to the original model ID are automatically routed to the upgraded version:

​

Deprecation Policy

*Depends on usage and whether there’s an available newer version of the model.

• Users of models scheduled for deprecation will be notified by email.
• All changes will be reflected on this page.
• Each deprecated model will have a specified removal date.
• After the removal date, the model will no longer be queryable via its serverless endpoint but options to migrate will be available as described below.

​

Migration Options

When a model is deprecated on our serverless platform, users have three options:

1. On-demand Dedicated Endpoint (if supported):
   • Reserved solely for the user, users choose underlying hardware.
   • Charged on a price per minute basis.
   • Endpoints can be dynamically spun up and down.
2. Monthly Reserved Dedicated Endpoint:
   • Reserved solely for the user.
   • Charged on a month-by-month basis.
   • Can be requested via this form.
3. Migrate to a newer serverless model:
   • Switch to an updated model on the serverless platform.

​

Migration Steps

1. Review the deprecation table below to find your current model.
2. Check if on-demand dedicated endpoints are supported for your model.
3. Decide on your preferred migration option.
4. If choosing a new serverless model, test your application thoroughly with the new model before fully migrating.
5. Update your API calls to use the new model or dedicated endpoint.

​

Deprecation History

All deprecations are listed below, with the most recent deprecations at the top. **Notes on model support: **

• Models marked “Yes” in the on-demand dedicated endpoint support column can be spun up as dedicated endpoints with customizable hardware.
• Models marked “No” are not available as on-demand endpoints and will require migration to a different model or a monthly reserved dedicated endpoint.

​

Recommended Actions

• Regularly check this page for updates on model deprecations.
• Plan your migration well in advance of the removal date to ensure a smooth transition.
• If you have any questions or need assistance with migration, please contact our support team.

For the most up-to-date information on model availability, support, and recommended alternatives, please check our API documentation or contact our support team.