isitdeprecated.com
collectors 5/5 ok last sync state ok models 2,537 events 7,802

DEPRECATED

Retired 2026-02-25 — 203 days ago. Requests to this identifier are expected to fail. Sources disagree on: max_output_tokens.

state=dead sunset=2026-02-25 days_remaining=-203 severity=critical sources=litellm,openrouter evidence_tier=catalog confirmed_by_endpoint=false documented_by_provider=false replacement=none corroborated=yes divergent_fields=max_output_tokens checked=2026-09-16 03:02Z

alibaba/qwen3-next-80b-a3b-thinking

Vendor: alibaba. Tracked by 2 of 5 sources.

What each source reports

SourceIDContext Max outIn $/Mtok Out $/MtokSunset
litellmdashscope/qwen3-next-80b-a3b-thinking262,14465,536$0.15$1.22026-02-25
openrouterqwen/qwen3-next-80b-a3b-thinking262,14432,768$0.15$1.2
endpoint = the provider's own machine-readable API, the strongest evidence. provider docs = the provider's own documentation, read by a model — first-party content, inferred reading. Unlabelled rows are third-party catalogs. Where sources disagree both values are shown rather than silently reconciled.

Change history

SeverityChangeWhat Detected
highmodifiedqwen/qwen3-next-80b-a3b-thinking: max_output_tokens cut 235,929 to 32,7682026-09-15
lowmodifiedqwen/qwen3-next-80b-a3b-thinking: max_output_tokens raised 32,768 to 235,9292026-09-07
lowaddednew model nebius/Qwen/Qwen3-Next-80B-A3B-Thinking (128,000 ctx)2026-09-06
lowaddednew model openrouter/qwen/qwen3-next-80b-a3b-thinking (262,144 ctx)2026-09-06
lowaddednew model qwen_ai_platform/qwen3-next-80b-a3b-thinking (262,144 ctx)2026-09-01
lowaddednew model qwencloud/qwen3-next-80b-a3b-thinking (262,144 ctx)2026-09-01
highmodifiedqwen/qwen3-next-80b-a3b-thinking: capabilities lost logit_bias2026-08-27
infodeprecatedtogether_ai/Qwen/Qwen3-Next-80B-A3B-Thinking: deprecation announced for 2026-02-25 (date already passed)2026-08-26
infodeprecatedtogether_ai/Qwen/Qwen3-Next-80B-A3B-Thinking: retires 2026-02-25 (182 days ago)2026-08-26
highmodifiedqwen/qwen3-next-80b-a3b-thinking: max_output_tokens cut 262,144 to 32,7682026-08-13
lowmodifiedqwen/qwen3-next-80b-a3b-thinking: max_output_tokens raised 32,768 to 262,1442026-08-11
highmodifiedqwen/qwen3-next-80b-a3b-thinking: max_output_tokens cut 262,144 to 32,7682026-08-10