Baseten ships four major open models day one, hits 668 tok/s on DeepSeek v4.1 Flash
baseten · x · 2026-10-21
Inference provider Baseten says every major open model launched this month went live on day zero: DeepSeek v4.1 Flash, Reflection Beam 1.0, NVIDIA Nemotron Super 3.5 VL, and Meta Muse Spark Open — each ranking first or second on both Artificial Analysis benchmarks and OpenRouter production traffic. Charts show DeepSeek v4.1 Flash at 668 tok/s on Baseten (FAST) vs 211 on DeepSeek's own API; Beam 1.0 at 532 tok/s but priced at $1.30/$4.30 per M tokens, well above CoreWeave's $0.30/$1.00. The pitch: benchmark scores matter less than consistent production performance.
Related event: Baseten day-one launch of top open models with fast inference(2 posts)→
More from Infra
- xAI said to lean on ACC/AEC and copper as Chinese pluggables stay off-limits — jwt0625 · 2026-10-21
- Packed a16z SF infra event features fal, ElevenLabs, BFL and Krea engineers — venturetwins · 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
- Modal Engineers Detail Sticky Serverless Routing for Real-Time AI Inference — blelbach · 2026-10-21
- EdgeKernelBench: LLM-Generated Kernels Hit 64.5% Correct but Only 25.5% Fast on Edge Backends — encodelab · 2026-10-21
- Meta Open-Sources Dist-MoE, Speeding MoE Training Up to 1.40x on GB300 NVL72 — ezyang · 2026-10-21