Deprecation

To continuously improve service quality, Ant Ling regularly introduces newer model versions with better performance and lower cost, while retiring older versions. This page outlines the deprecation policy, deprecated models, and migration recommendations.

Deprecation Policy

Advance notice: We will notify users via documentation and announcements before a model is officially deprecated.
Service termination: After the deprecation date, API calls using the affected model ID will return errors and no longer be served.
Smooth migration: Each deprecated model comes with a recommended replacement that is no worse in performance and cost than the original.

Deprecated Models

Upcoming Deprecation

The following models will be retired on November 15, 2026 at 00:00:00 (UTC+8). Please migrate to the recommended replacements as soon as possible to avoid request failures once the deprecation takes effect.

Model ID	Family	Planned Deprecation Date	Recommended Replacement
`Ling-2.6-1T`	Ling 2.6	2026-11-15 00:00:00 (UTC+8)	`Ling-3.1-flash`
`Ring-2.6-1T`	Ring 2.6	2026-11-15 00:00:00 (UTC+8)	`Ling-3.1-flash`
`Ling-2.6-flash`	Ling 2.6	2026-11-15 00:00:00 (UTC+8)	`Ling-3.1-flash`

Already Deprecated

The following models have been retired. Please migrate to the recommended replacements.

Model ID	Family	Deprecation Date	Recommended Replacement
`Ling-1T`	Ling 2.0	2026-06-15 00:00:00 (UTC+8)	`Ling-3.1-flash`
`Ring-1T`	Ring 2.0	2026-06-15 00:00:00 (UTC+8)	`Ling-3.1-flash`
`Ling-2.5-1T`	Ling 2.5	2026-09-30 00:00:00 (UTC+8)	`Ling-3.1-flash`
`Ring-2.5-1T`	Ring 2.5	2026-09-30 00:00:00 (UTC+8)	`Ling-3.1-flash`

Currently Available Models

The following models are in stable support and can be safely used in production.

Model ID	Family	Description
`Ling-3.1-flash`	Ling 3.1	New-generation hybrid reasoning model, purpose-built for everyday office work, long-horizon software development, and complex Agent tasks
`Ling-3.0-flash-VL`	Ling 3.0	Native multimodal hybrid reasoning model, supports image, text, and video input
`Ling-3.0-flash`	Ling 3.0	Cost-efficient hybrid reasoning model for high-frequency tasks
`Ling-3.0-tiny`	Ling 3.0	Lightweight hybrid reasoning model, supports on-device deployment and local offline execution

Migration Guide

Ling

Replace the legacy model ID in your code with the corresponding new version:


# Legacy (deprecated)
model="Ling-1T"
 
# New (recommended)
model="Ling-3.1-flash"    # New-generation hybrid reasoning model

Selection guidance:

Previously used Ling-1T / Ling-2.5-1T / Ling-2.6-1T / Ling-2.6-flash → migrate to Ling-3.1-flash, which offers stronger performance and lower cost, covering everyday chat, complex reasoning, long-context, and agentic task scenarios.

Ring


# Legacy (deprecated)
model="Ring-1T"
 
# New (recommended)
model="Ling-3.1-flash"

Previously used Ring-1T / Ring-2.5-1T / Ring-2.6-1T → migrate to Ling-3.1-flash, the new-generation hybrid reasoning model covering complex reasoning and agentic task scenarios.

Third-Party Platforms

When integrating via Zenmux, update the model ID to the new version as well:


# Zenmux
inclusionai/ling-3.1-flash

For any questions, refer to the OpenRouter integration guide or Zenmux integration guide.

Was this page helpful?