
DeepSeek R1
DeepSeek R1 is DeepSeek's open reasoning model, trained with large-scale reinforcement learning on top of DeepSeek-V3-Base. It's a 671B-parameter mixture of experts with 37B active per token and a 128K context window.
Ways to run DeepSeek R1
Dedicated endpoint
Get a quote →Your own GPUs, tuned for your traffic. We profile your workload, tune the deployment and put throughput and latency in your contract.
Serverless
API docs →Pay per token on shared GPUs, with no capacity to plan or reserve.
Inside your network
Security →Run a dedicated endpoint inside your own network, including air-gapped environments.
Pricing
Use it with the agents we set up for you
Point any open-source agent at your endpoint, or pick from our catalog and we set it up as part of your contract.
DeepSeek R1 FAQ
How much does DeepSeek R1 cost on Saturn Cloud?
Serverless costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. A dedicated endpoint is priced per GPU-hour for the GPUs it runs on, and we size the GPUs to your traffic.
What settings does DeepSeek recommend for R1?
Temperature between 0.5 and 0.7, with 0.6 recommended. Skip the system prompt and put all instructions in the user prompt. For math, ask for step-by-step reasoning with the final answer in \boxed{}.
How do I make sure DeepSeek R1 reasons?
The model sometimes skips its reasoning. DeepSeek recommends making every output start with <think>.
Are the distilled versions of DeepSeek R1 available?
Yes, on dedicated endpoints. DeepSeek released six distilled models at 1.5B, 7B, 8B, 14B, 32B and 70B, built on Qwen2.5 and Llama, and all six are in our catalog.
How does DeepSeek R1 compare with DeepSeek V4 Flash?
R1 has a 128K context window and always reasons. V4 Flash has a 1M-token context window and three reasoning modes. On serverless, R1 costs $0.15 input and $0.60 output per 1M tokens, and V4 Flash costs $0.075 and $0.30.