Together AI raises GPU cluster reserved rates, unifies speech-to-text pricing
Together AI raised GPU cluster reserved H100 rates and unified speech-to-text pricing at $0.0015/audio-minute, cutting Nemotron 3.5 ASR pricing 67%.
GPU Cluster reserved H100: $3.59/hr (7-30d), $3.29 (31-90d), $3.09 (91-180d); STT metered per-character for Parakeet ($0.0035/1M chars) and Nemotron 3 ASR ($0.0015/1M chars), per-minute for Whisper ($0.0015/min), Whisper Streaming ($0.0035/min), and Nemotron 3.5 ASR ($0.0045/min)
GPU Cluster reserved H100: $3.69/hr (7-30d), $3.45 (31-90d), $3.19 (91-180d); all four serverless speech-to-text models (Whisper Large v3, Parakeet TDT 0.6B v3, Nemotron 3 ASR Streaming, Nemotron 3.5 ASR Streaming) now bill at a unified $0.0015 per audio minute
Together’s managed GPU Cluster reserved H100 rate rose for the first time since the aggressive back-to-back cuts of June 2026 — up to $3.69/hr on a 7-30 day reservation (from $3.59), $3.45/hr on 31-90 days (from $3.29), and a $3.19/hr floor on 91-180 days (from $3.09). On-demand H100, and every published H200/B200 on-demand and reserved rate, held flat, so the increase is isolated to the reserved-H100 tenors.
In the same capture cycle, Together’s speech-to-text catalog was re-metered onto a single unit. Previously the four serverless STT models split across two different meters — per-1M-characters for Parakeet TDT 0.6B and Nemotron 3 ASR, per-audio-minute for Whisper and Nemotron 3.5 ASR — at four different rates. All four now bill at a flat $0.0015 per audio minute, which is a like-for-like 67% cut on Nemotron 3.5 ASR (from $0.0045/min) and a unit change (character to minute) for Parakeet and Nemotron 3 ASR. The serverless chat catalog also grew (Kimi K3, Gemma 4 31B, Qwen3.7-Plus, LFM2.5-8B-A1B) without moving any previously-published per-model rate.
Together's GPU Cluster reserved H100 rate rose across all three commitment tenors for the first time since the back-to-back June 2026 cuts: 7–30 day $3.59→$3.69/hr, 31–90 day $3.29→$3.45/hr, and the 91–180 day floor $3.09→$3.19/hr. On-demand H100 and every H200/B200 on-demand and reserved rate held flat, so the increase is isolated to reserved-H100 tenors. In the same capture cycle, all four serverless speech-to-text models (Whisper Large v3, Parakeet TDT 0.6B v3, and both Nemotron 3 and 3.5 ASR Streaming variants) were unified onto a single $0.0015-per-audio-minute meter — a 67% cut on Nemotron 3.5 ASR (from $0.0045/min) and a billing-unit change (from per-1M-characters to per-audio-minute) for Parakeet TDT 0.6B and Nemotron 3 ASR. Four new serverless chat models (Kimi K3, Gemma 4 31B, Qwen3.7-Plus, LFM2.5-8B-A1B) joined the catalog without moving any previously-published rate.