Inference Serverless rate limit ceilings now scale by model size Serverless adaptive rate limit ceilings now...
UpdateUnverifiedAdded Sep 24, 2026
Inference Serverless rate limit ceilings now scale by model size Serverless adaptive rate limit ceilings now vary by model size tier. Smaller models ( Serverless rate limits for tier thresholds and ceiling values.
More Fireworks AI platform releases
Every Fireworks AI platform release| Date | Release | Type |
|---|---|---|
| Aug 31 | Training New Serverless Training models: DeepSeek V4 Flash 0731, Qwen 3.8 27B, and Muse Glimmer 30B The...unverified Update | Update |
| Aug 29 | Recommended migrationsunverified 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 |
| Sep 8 | Platform Deployment tags and annotation API changes Deployment tags are customer-managed entries stored in a...unverified Update | Update |
| Aug 25 | Platform SSO documentation: IdP-initiated SAML Updated the Custom SSO guideunverified Update | Update |
| Sep 10 | Training Training cost estimator The new training cost estimator helps you estimate what a training job will...unverified Update | Update |
| Sep 12 | Action requiredunverified Update | Update |
| Sep 12 | Recommended migrationsunverified Update | Update |
Also shipped on Sep 1, 2026
Fireworks AI in September 2026
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.