Baseten launches DeepSeek V4 Flash and Inkling-Small, renames DeepSeek V4 to Pro
Baseten added DeepSeek V4 Flash and Inkling-Small to its Model APIs catalog (now 12 models), renaming DeepSeek V4 to DeepSeek V4 Pro at unchanged rates.
10 Model APIs SKUs: Kimi K3, GLM-5.2 Fast, Inkling, GLM-5.2, GLM 4.7, Kimi K2.7 Code, Kimi K2.6, NVIDIA Nemotron 3 Ultra, DeepSeek V4 ($1.74 in / $0.145 cache / $3.48 out), GPT OSS 120B.
12 Model APIs SKUs adding DeepSeek-V4-Flash-0731 ($0.13 in / $0.028 cache / $0.26 out) and Inkling-Small ($0.50 / $0.10 / $1.20); DeepSeek V4 renamed DeepSeek V4 Pro (rates unchanged: $1.74 / $0.145 / $3.48).
Eight days after growing its Model APIs catalog to ten models with Kimi K3 and GLM-5.2 Fast, Baseten expanded the roster again to twelve — this time at the cheap end of the rate card. DeepSeek-V4-Flash-0731 launched as the platform’s lowest-priced frontier-derived model at $0.13 input / $0.028 cache input / $0.26 output per 1M tokens, promoted by a homepage banner (“Try the new DeepSeek V4 Flash today. Frontier intelligence at a fraction of the cost.”) that replaced the prior “Announcing our Series F” funding banner. Inkling-Small joined alongside it at $0.50 / $0.10 / $1.20, a smaller and cheaper sibling to the existing Inkling line.
The existing DeepSeek V4 SKU was simultaneously renamed DeepSeek V4 Pro to disambiguate it from the new Flash variant — its $1.74 input, $0.145 cache input, and $3.48 output rates did not change. No other pricing surface moved: dedicated deployment GPU/CPU rates, the on-demand Training rate card, and the Basic/Pro/Enterprise tier structure are all unchanged from the prior capture.
Six days after growing to ten models, Baseten added DeepSeek-V4-Flash-0731 ($0.13 input / $0.028 cache input / $0.26 output per 1M tokens — the platform's cheapest model to date) and Inkling-Small ($0.50 / $0.10 / $1.20), and renamed the existing DeepSeek V4 SKU to DeepSeek V4 Pro at unchanged rates ($1.74 / $0.145 / $3.48). The homepage banner switched from an 'Announcing our Series F' funding promo to a DeepSeek V4 Flash product promo. Dedicated GPU/CPU/Training rate cards and the Basic/Pro/Enterprise tier structure were unchanged.