Reference Source

qwen-3-32b — Deprecated or End-of-Life or Removed — sources disagree

For qwen-3-32b, provider is Cerebras; lifecycle status is disputed: Deprecated per inference-docs.cerebras.ai, Deprecated per docs.sambanova.ai, End-of-Life per console.groq.com, 1 more; deprecation announced is disputed: 2026-02-16 per inference-docs.cerebras.ai, March 31, 2026 per docs.sambanova.ai, June 17, 2026 per console.groq.com; recommended replacement is disputed: GPT OSS 120B per inference-docs.cerebras.ai, MiniMax-M2.5 per docs.sambanova.ai, openai/gpt-oss-120b per console.groq.com, 1 more; platform / deployment scope is Cerebras Inference API, recorded from its source on 2026-09-09; source re-checked 2026-11-11.

Provider
Cerebras our reading
SambaNova per docs.sambanova.ai
Groq per console.groq.com
Nebius Token Factory per docs.tokenfactory.nebius.com
Model ID / API name
qwen-3-32b verified
Lifecycle status
Deprecated sources disagree
Deprecation announced
2026-02-16 sources disagree
Recommended replacement
GPT OSS 120B sources disagree
Platform / deployment scope
Cerebras Inference API our reading
SambaNova SambaCloud per docs.sambanova.ai
Free and developer-tier usage — enterprise customers with a committed-spend contract are not affected per console.groq.com
Nebius Token Factory serverless (dedicated endpoints unaffected) per docs.tokenfactory.nebius.com
Shutdown / retirement date
4/6/2026 per docs.sambanova.ai
Sourceinference-docs.cerebras.ai
Verified
Review by
DatasetAI model deprecation and retirement dates by provider

Values marked our reading are our classification of what the source says — the source does not print them in those words. The quote below is the evidence for each one; judge it yourself.

What the source says

2026-02-16 Deprecated qwen-3-32b and llama-3.3-70b We recommend migrating to GPT OSS 120B.

— inference-docs.cerebras.ai, retrieved 2026-09-09

Sources disagree

More than one authority states this, and they do not state the same thing. Both are reproduced with the source each came from — deciding between them is yours, not ours.

Lifecycle status

inference-docs.cerebras.ai says lifecycle status is Deprecated, as of 2026-09-09.

2026-02-16 Deprecated qwen-3-32b and llama-3.3-70b We recommend migrating to GPT OSS 120B.

https://inference-docs.cerebras.ai/support/deprecation

docs.sambanova.ai says lifecycle status is Deprecated, as of 2026-09-15.

| `Qwen3-32B` | 4/6/2026 | `MiniMax-M2.5` |

https://docs.sambanova.ai/docs/en/models/deprecations.md

console.groq.com says lifecycle status is End-of-Life, as of 2026-09-21.

| qwen/qwen3-32b | 07/17/26 | openai/gpt-oss-120b |

https://console.groq.com/docs/deprecations.md

docs.tokenfactory.nebius.com says lifecycle status is Removed, as of 2026-09-16.

| [`Qwen/Qwen3-32B`](https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B) | [`nvidia/Nemotron-3_5-Lightning`](https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning) |

https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md

Deprecation announced

inference-docs.cerebras.ai says deprecation announced is 2026-02-16, as of 2026-09-09.

2026-02-16 Deprecated qwen-3-32b and llama-3.3-70b We recommend migrating to GPT OSS 120B.

https://inference-docs.cerebras.ai/support/deprecation

docs.sambanova.ai says deprecation announced is March 31, 2026, as of 2026-09-15.

| `Qwen3-32B` | 4/6/2026 | `MiniMax-M2.5` |

https://docs.sambanova.ai/docs/en/models/deprecations.md

console.groq.com says deprecation announced is June 17, 2026, as of 2026-09-21.

| qwen/qwen3-32b | 07/17/26 | openai/gpt-oss-120b |

https://console.groq.com/docs/deprecations.md

Recommended replacement

inference-docs.cerebras.ai says recommended replacement is GPT OSS 120B, as of 2026-09-09.

2026-02-16 Deprecated qwen-3-32b and llama-3.3-70b We recommend migrating to GPT OSS 120B.

https://inference-docs.cerebras.ai/support/deprecation

docs.sambanova.ai says recommended replacement is MiniMax-M2.5, as of 2026-09-15.

| `Qwen3-32B` | 4/6/2026 | `MiniMax-M2.5` |

https://docs.sambanova.ai/docs/en/models/deprecations.md

console.groq.com says recommended replacement is openai/gpt-oss-120b, as of 2026-09-21.

| qwen/qwen3-32b | 07/17/26 | openai/gpt-oss-120b |

https://console.groq.com/docs/deprecations.md

docs.tokenfactory.nebius.com says recommended replacement is nvidia/Nemotron-3_5-Lightning, as of 2026-09-16.

| [`Qwen/Qwen3-32B`](https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B) | [`nvidia/Nemotron-3_5-Lightning`](https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning) |

https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md

Where the other sources' values come from

These values were taken from a passage elsewhere on the other source's page, not from the row quoted with it above.

Lifecycle status

This document outlines the deprecation process, provides guidance on migration, and maintains a historical record of deprecated models with their recommended alternatives.

— docs.sambanova.ai, retrieved 2026-09-15

Deprecation announced

On March 31, 2026, SambaNova notified users of the following model deprecations.

— docs.sambanova.ai, retrieved 2026-09-15

Deprecation announced

In line with our commitment to bringing you cutting-edge models, on June 17, 2026, we emailed users to announce the deprecation of `qwen/qwen3-32b` and `meta-llama/llama-4-scout-17b-16e-instruct`

— console.groq.com, retrieved 2026-09-21

Platform / deployment scope

This deprecation applies to free and developer-tier usage; enterprise customers with a committed-spend contract are not affected.

— console.groq.com, retrieved 2026-09-21

Platform / deployment scope

Affected Serverless models will no longer be available via API or Playground.

— docs.tokenfactory.nebius.com, retrieved 2026-09-16

Sources

Last verified against source: . Due for re-check by . This page as Markdown · OKF bundle · full dataset as JSON.

This one changes, and we watch it.AI model deprecation and retirement dates by provider is re-read on a schedule and every change is dated. Subscribe: Atom feed · JSON · what has changed so far.

More on software, security and the internet

All 21 datasets on this subject · Look something up