Baseten adds DeepSeek V4.1 Flash 1017 at $0.30/$1.20 per 1M tokens

Baseten added a new row to its Model APIs catalog for DeepSeek V4.1 Flash 1017, priced at $0.30 per 1M input tokens, $0.007 per 1M cached input tokens, and $1.20 per 1M output tokens. The previous change, one day earlier on Oct 17, added Reflection Beam ($1.30 input, $0.13 cached, $4.30 output per 1M tokens) and Meta Muse Spark Open ($1.25/$0.15/$4.25); before that, Nemotron 3.5 Super VL was added on Oct 16 at $0.20 per 1M input tokens.

Model-hosting platforms like Baseten compete less on subscription tiers and more on how fast and cheaply they can expose new models. DeepSeek V4.1 Flash 1017 extends a fast pace of catalog additions this week — Nemotron on Oct 16, Reflection Beam and Meta Muse Spark Open on Oct 17 — well ahead of Baseten's baseline cadence of about every 17 days. That speed is itself a form of pricing pressure on rivals racing to list the same models at competitive per-token rates. Watch whether Baseten's near-daily additions settle back into its slower historical cadence, or whether this marks a lasting shift to faster, more frequent catalog updates as new open models ship.