Inference Serverless deprecation: MiniMax M2.5 MiniMax M2.5 is deprecated from serverless
DeprecationUnverifiedAdded Sep 24, 2026
Inference Serverless deprecation: MiniMax M2.5 MiniMax M2.5 is deprecated from serverless. Migrate to MiniMax M2.7 .
More Fireworks AI platform releases
Every Fireworks AI platform release| Date | Release | Type |
|---|---|---|
| Jun 20 | Recommended migrationsunverified Update | Update |
| Jul 17 | Training SFT learning rate scheduler documentation Documented learning rate scheduler settings for supervised...unverified Update | Update |
| Aug 15 | Inference Serverless deprecation: DeepSeek V4 Flash DeepSeek V4 Flash is deprecated from serverlessunverified Deprecation | Deprecation |
| Aug 25 | Platform SSO documentation: IdP-initiated SAML Updated the Custom SSO guideunverified Update | Update |
| Aug 28 | Training Serverless Training deprecation: Qwen 3.5 9B and Qwen 3.6 27B Qwen 3.5 9B and Qwen 3.6 27B are...unverified Deprecation | Deprecation |
| Aug 29 | Recommended migrationsunverified Update | Update |
| Aug 31 | Training New Serverless Training models: DeepSeek V4 Flash 0731, Qwen 3.8 27B, and Muse Glimmer 30B The...unverified Update | Update |
| Sep 1 | Inference Serverless rate limit ceilings now scale by model size Serverless adaptive rate limit ceilings now...unverified Update | Update |
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.