DeepSeek V4.1 Flash supports priority pay-per-token and reserved provisioned throughput
UpdateyesterdayUnverifiedAdded Oct 8, 2026
You can now use DeepSeek V4.1 Flash with priority pay-per-token for latency-sensitive traffic or reserved provisioned throughput for dedicated capacity.
Topics: Performance
More Databricks Data Intelligence Platform releases
Every Databricks Data Intelligence Platform release- Zhipu AI GLM 5.2 is now a legacy model
Updateunverified
- DeepSeek V4 Flash (0731) is scheduled for retirement
Deprecationunverified
- ai_parse_document now extracts chart data as JSON
Updateunverified
- Standard ai_extract now delivers higher-quality extraction
Updateunverified
- Save reusable query templates in Google Sheets
Updateunverified
| Date | Release | Type |
|---|---|---|
| Oct 62 days ago | Zhipu AI GLM 5.2 is now a legacy model unverified Update | Update |
| Oct 62 days ago | Deprecation | Deprecation |
| Oct 53 days ago | Update | Update |
| Oct 53 days ago | Update | Update |
| Oct 26 days ago | Update | Update |
| Oct 26 days ago | GA | GA |
| Oct 26 days ago | Update | Update |
| Oct 17 days ago | Preview | Preview |
Also shipped on Oct 7, 2026
Databricks in October 2026- SSH for Cloud Run services and instances is in Preview
Google CloudPreviewunverified
- Set credit usage limits and alerts for your workspace
LovablePricingunverified
- Faster inline text edits
LovablePreviewunverified
- Gemini 3.7 Flash is deprecated for your app's AI features
LovableDeprecationunverified
- The Cost Analysis tab of the Billing page now includes Serverless Inference Live Usage, which lists the...
DigitalOceanPricingunverified
| Date | Company | Release | Product | Type |
|---|---|---|---|---|
| Oct 7yesterday | Google Kubernetes Engine | GA | ||
| Oct 7yesterday | Cloud Run | Preview | ||
| Oct 7yesterday | Lovable | Pricing | ||
| Oct 7yesterday | Faster inline text edits unverified | Lovable | Preview | |
| Oct 7yesterday | Lovable | Deprecation | ||
| Oct 7yesterday | DigitalOcean | Pricing |