Skip to content
Model Change Index
  • OverviewNext shutdowns and latest changes
  • ShutdownsEvery date, one row per platform
  • ChangesReleases, deprecations, redirects and prices
  • LeaderboardEvery model, its scores and price
  • Check my stackYour models on one timeline
Track my stack

Qwen3.5-397B-A17B

ActiveAlibaba Cloud (Qwen)alibaba/qwen3-5-397b-a17b2 platforms

Shutting down. Qwen3.5-397B-A17B shuts down on Azure AI Foundry on Jul 1, 2027. Alibaba Cloud (Qwen) names MiniMax-M3 as the replacement.

9 mo
Next shutdown
260 daysJul 1, 2027 · Azure AI Foundry
Arena Text
1,442#48 of 128 · Arena
GPQA Diamond
86.4%#51 of 108 · Epoch AI
Context window
262.1Ktokens

Dates on every platform

2 listings · a floor is the earliest possible date
Qwen3.5-397B-A17B on each platform: model ID, status, dates, replacement and source
PlatformModel ID and statusDeprecatedShuts downReplacement
Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026FW-Qwen3.5-397B-A17B:1Active––
Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026Qwen/Qwen3.5-397B-A17BShut down–MiniMax-M3

Served by Fireworks through Foundry. Fireworks per-token models carry a 15-day retirement notice.

What breaks when you move off Qwen3.5-397B-A17B

  • Availability

    Requests to the removed serverless model ID fail. The model can still run on an on-demand dedicated endpoint, billed per minute.

    Qwen3.5-397B-A17B to MiniMax-M3 · Together AI ·

Intelligence

Third-party results, credited below
Third-party benchmark scores for Qwen3.5-397B-A17B
BenchmarkPublisherScoreRankPublished
Arena TextArena1,442 ± 2#48 of 128Oct 8, 2026
GPQA DiamondEpoch AI86.4% ± 2.4%#51 of 108Aug 7, 2026
Arena WebDevArena1,400 ± 3#45 of 69Oct 8, 2026
FrontierMath Tiers 1-3Epoch AI31.2% ± 2.7%#57 of 71Aug 30, 2026
OTIS Mock AIME 2024-2025Epoch AI88.9% ± 4.7%#47 of 105Aug 7, 2026

Arena (arena.ai), https://arena.ai/leaderboard

Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].

Change history

ShutdownQwen3.5 397B leaves Together serverlessTogether AI1 break

Together removed Qwen/Qwen3.5-397B-A17B from serverless inference and recommends MiniMax-M3.

Platform
Together AI
Replacement
MiniMax-M3
Announced
  • AvailabilityRequests to the removed serverless model ID fail. The model can still run on an on-demand dedicated endpoint, billed per minute.

Source: Together AI, Changelog (opens in a new tab); Together AI, Deprecations (opens in a new tab)

Built by TeqEngine. Forward-deployed AI engineering, no model to sell. Moving an agent to a new model? Ask for a Next-Model Check.