MiniMax-M2.7

Shut downMiniMaxminimax/minimax-m2-72 platforms

What breaks Add its dates to my calendar

Next shutdown: None setNo date on 2 platforms
Arena Text: 1,415#65 of 128 · Arena
Arena WebDev: 1,398#46 of 69 · Arena

Dates on every platform

2 listings · a floor is the earliest possible date

MiniMax-M2.7 on each platform: model ID, status, dates, replacement and source
Platform	Model ID and status	Deprecated	Shuts down	Replacement
Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026	`MiniMaxAI/MiniMax-M2.7`Shut down	–	Jul 28, 2026Shut down	–
Fireworks AIFireworks AI: MiniMax M2.7 model page (opens in a new tab) · checked Oct 14, 2026	`accounts/fireworks/models/minimax-m2p7`Shut down	–	Aug 27, 2026Shut down	MiniMax-M3

Removal is recorded in the changelog for 28 July 2026; the deprecation history table does not list it.

Removed from serverless only; dedicated deployments of this model are unaffected.

What breaks when you move off MiniMax-M2.7

Availability
Serverless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.
MiniMax-M2.7, gpt-oss-20b, DeepSeek-V4-Pro, Kimi K2.6, Kimi K2.7 Code · Fireworks AI · Aug 27, 2026

Intelligence

Third-party results, credited below

Third-party benchmark scores for MiniMax-M2.7
Benchmark	Publisher	Score	Rank	Published
Arena Text	Arena	1,415 ± 2	#65 of 128	Oct 8, 2026
Arena WebDev	Arena	1,398 ± 3	#46 of 69	Oct 8, 2026

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

Change history

Aug 27, 2026ShutdownFireworks removes MiniMax M2.7, GPT OSS 20B, DeepSeek V4 Pro and fast Kimi variants from serverlessFireworks AI1 break

MiniMax M2.7, GPT OSS 20B and the original DeepSeek V4 Pro left serverless, along with the Turbo and Fast variants of Kimi K2.6 and the Fast variant of Kimi K2.7 Code. Fireworks named MiniMax M3, GPT OSS 120B, DeepSeek V4 Pro (0813) and the standard Kimi modes as migration targets.

Platform: Fireworks AI
Models: MiniMax-M2.7, gpt-oss-20b, DeepSeek-V4-Pro, Kimi K2.6, Kimi K2.7 Code

AvailabilityServerless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.

Source: Fireworks AI, Changelog (opens in a new tab)

Jul 28, 2026ShutdownMiniMax M2.7 leaves Together serverlessTogether AI

Together removed MiniMaxAI/MiniMax-M2.7 from serverless inference.

Platform: Together AI
Model: MiniMax-M2.7

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

Jun 17, 2026ShutdownMiniMax M2.5 leaves Fireworks serverlessFireworks AI1 break

Fireworks deprecated MiniMax M2.5 from serverless and named MiniMax M2.7 as the migration target.

Platform: Fireworks AI
Model: MiniMax-M2.5
Replacement: MiniMax-M2.7

AvailabilityServerless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.

Source: Fireworks AI, Changelog (opens in a new tab)

Jun 4, 2026ShutdownQwen3 Coder 480B leaves Together serverlessTogether AI1 break

Together removed Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 from serverless inference and recommended MiniMax-M2.7, itself removed on 28 July 2026.

Platform: Together AI
Model: Qwen3-Coder-480B-A35B-Instruct
Replacement: MiniMax-M2.7

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)