Serving
ReleaseWorth evaluating
DeepSeek V4.1 Flash gains priority pay-per-token and reserved throughput
From Databricks release notes (AWS)
DeepSeek V4.1 Flash can now be served with priority pay-per-token for latency-sensitive traffic, or with reserved provisioned throughput for dedicated capacity.
What to re-read
More from Serving
- DeprecatedDeepSeek V4 Flash (0731) will be retired on 5 November 2026
- DeprecatedDeepSeek V4 Pro (0813) ends on 2026-10-30
- ReleaseOpenJev (Qwen3.5 4B) is available on Unity Gateway
- DeprecatedThinking Machine Labs Inkling will retire on October 30, 2026