Baseten day-one launch of top open models with fast inference

Inference platform Baseten launched all major open models on day one this month, including DeepSeek v4.1 Flash, which reached 668 tok/s, claiming top performance in both benchmarks and production traffic.

2026-10-21 ~ 2026-10-21 · 2 related posts

• Baseten ships four major open models day one, hits 668 tok/s on DeepSeek v4.1 Flash — baseten · 2026-10-21
• Baseten ships DeepSeek v4.1 Flash, Reflection Beam 1.0, Nemotron Super 3.5 VL day-zero with claimed top benchmarks — baseten · 2026-10-21