Reserve dedicated GPUs
Your model on GPUs reserved for you.
- Throughput and latency SLA
- Tuned for your traffic
- Catalog models, your own
models and fine-tunes
PRICING
Your model on GPUs reserved for you.
No capacity to plan or reserve.
GPUs reserved for your endpoint.
Per month assumes 730 hours, one GPU running around the clock.
| GPU | MEMORY | GOOD FOR | LIST / HOUR |
|---|---|---|---|
| L40S | 48 GB | Small models, embeddings and vision | $1.10 |
| RTX PRO 6000 | 96 GB | Mid-size models on one GPU | $1.25 |
| H100 | 80 GB | General production LLM serving | $3.15 |
| H200 | 141 GB | Larger models and longer context | $3.80 |
| B200 | 180 GB | High-throughput serving | $5.95 |
| B300 | 288 GB | The largest open models | $6.65 |
| GB300 NVL72 | 288 GB per GPU | Very large models across 72 GPUs | Priced per deal |
Price per 1M tokens on shared GPUs.
| MODEL | INPUT | OUTPUT |
|---|---|---|
| Kimi K3moonshotai/Kimi-K3 | $0.75 | $3.75 |
| GLM 5.3zai-org/GLM-5.3 | $0.35 | $1.10 |
| NVIDIA Nemotron 3 Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | $0.15 | $0.60 |
| DeepSeek R1deepseek-ai/DeepSeek-R1 | $0.15 | $0.60 |
| MiniMax M3MiniMaxAI/MiniMax-M3 | $0.075 | $0.30 |
| DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash | $0.075 | $0.30 |
| GLM 4.6zai-org/GLM-4.6 | $0.075 | $0.30 |
| Qwen3 235B InstructQwen/Qwen3-235B-A22B-Instruct-2507 | $0.075 | $0.30 |
| gpt-oss-120bopenai/gpt-oss-120b | $0.04 | $0.15 |
| NVIDIA Nemotron 3.5 Lightning 30Bnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | $0.0125 | $0.05 |
| Qwen3 Coder 30BQwen/Qwen3-Coder-30B-A3B-Instruct | $0.0125 | $0.05 |
| No listed model matches. Other open models are priced by size below. | ||
For open models not listed above.
| MODEL SIZE | INPUT AND OUTPUT, PER 1M TOKENS |
|---|---|
| Dense, under 4B | $0.025 |
| Dense, 4B to 16B | $0.05 |
| Dense, over 16B | $0.225 |
| Mixture of experts, up to 56B | $0.125 |
| Mixture of experts, 56B to 176B | $0.30 |
| Mixture of experts, over 176B | On request |
Most dedicated quotes come in below list price.
ESTIMATED MONTHLY COST AT LIST
$18,396
$25.20 per hour for the whole endpoint
8 × H100 × $3.15 per GPU-hour × 730 hours
We size the GPUs to your traffic.
Talk to an engineerESTIMATED MONTHLY COST
$750.00
$1.25 per 1M tokens, blended
500M input × $0.75 per 1M tokens + 100M output × $3.75 per 1M tokens
Need an SLA? Use a dedicated endpoint.
See all token prices$5.95Saturn Cloud B200 list price
Dedicated inference
List price, $ per GPU-hour
2.4xGLM-5.3 throughput after tuning
GLM-5.3, 16 live sessions
Tokens per second per GPU, same four GB300 GPUs
List prices from each provider’s public pricing page.
Your model, traffic pattern, latency target and region.
We match GPUs and a region to the workload and send a quote.
We deploy, tune and benchmark the endpoint,
then commit to the measured performance.
FAQ
The capacity comes from neocloud partners and isn’t in a public catalog, so we quote each workload.
Yes. Serve a model from our catalog, bring your own, or fine-tune one on your data and serve the result from your dedicated endpoint.
Yes. Sign up for a free account to try the platform. When you’re ready for dedicated GPU capacity, talk to us.
We partner with neoclouds bringing new GPU capacity online, before it reaches the open market. We also tune each deployment, so you get more tokens from every GPU-hour.
Yes. The platform only needs a Kubernetes cluster, so it can run on-premises, in your cloud account, in air-gapped networks or in a specific region for data sovereignty.
Hourly rates for self-service accounts are on the Saturn Cloud Hosted page.
Send us your model and traffic. We’ll come back with a quote and the performance we’ll commit to.