RTX 6000 Ada pricing on Together AI
Every Together AI RTX 6000 Ada offering we track, normalized to a per-GPU hourly rate and ranked against 22 providers with current RTX 6000 Ada pricing.
The cheapest RTX 6000 Ada we currently track is $0.629/hr on Vast.ai.
Together AI RTX 6000 Ada rates
Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.
| Price / GPU-hr | Type | GPUs |
|---|---|---|
| $1.49 | On-demand | 1 |
| $1.49 | On-demand | 2 |
| $1.49 | On-demand | 4 |
| $1.49 | On-demand | 8 |
RTX 6000 Ada specifications
- VRAM
- 48GB
- Architecture
- Ada Lovelace
- CUDA Cores
- 18,176
- Tensor Cores
- 568
- Memory Bandwidth
- 960 GB/s
- TDP
- 300W
RTX 6000 Ada on other providers
- Vast.ai$0.629/hr
- Omega Gradient$0.680/hr
- IO.NET$0.682/hr
- Lium.io$0.690/hr
- Runpod$0.740/hr
- Fluence Cloud$0.760/hr
- Aquanode$0.771/hr
- gpu.ai$0.780/hr
- QuantaCloud$0.780/hr
- Spheron$0.780/hr
- Verda$0.787/hr
- Massed Compute$0.790/hr
- Hexgrid Cloud$0.880/hr
- Shadeform$0.970/hr
- Sesterce$1.07/hr
- AceCloud$1.14/hr
- Runcrate$1.31/hr
- centron$1.32/hr
- DigitalOcean$1.57/hr
- VoltageGPU$1.58/hr
- SwissGPU$2.41/hr
About Together AI
Together AI is the AI Native Cloud platform engineered for developers building with open-source and frontier AI models. They provide serverless inference, fine-tuning, and GPU clusters with inference and training performance optimizations.
Frequently Asked Questions
How much does the RTX 6000 Ada cost on Together AI?
Together AI lists the RTX 6000 Ada from $1.49 per GPU-hour across 4 tracked configurations. Prices are collected daily — see the table above for the current rates.
Is Together AI the cheapest place to rent the RTX 6000 Ada?
Together AI ranks #19 of 22 providers we track with current RTX 6000 Ada pricing. The cheapest right now is Vast.ai. Price is only one factor — region availability, network, and storage costs differ between providers.
Which RTX 6000 Ada configurations does Together AI offer?
We currently track 4 RTX 6000 Ada offerings from Together AI, covering the GPU counts, pricing types, and regions listed in the table above. Every price is normalized to a per-GPU hourly rate so it can be compared across providers.