High-Performance LLM
Inference at Low Cost
Deploy and scale LLM inference—serve models like Llama 4 and DeepSeek
on our low-cost GPU platform.
Pay-as-you-go APIs mean you pay only for the inference you use.
Kimi-K2-Instruct
Kimi K2 is a mixture-of-experts (MoE) language model with 1 trillion total parameters. Kimi K2 excels at knowledge, reasoning, and coding tasks, with strong agentic capabilities.
DeepSeek-R1-0528
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.
Llama-4-Maverick-17B-128E-Instruct
Maverick beats GPT‑4o on coding, vision, reasoning and remains lightweight for efficient local deployment.
Quick Start
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "https://inference.cloudrift.ai/v1",
apiKey: "YOUR_RIFT_API_KEY",
});
const completion = await openai.chat.completions.create({
model: "llama4:maverick",
messages: [
{
role: "user",
content: "What is the meaning of life?"
}
],
stream: true,
});
for await (const chunk of completion) {
process.stdout.write(chunk.choices[0]?.delta.content as string);
}All Available Models
Instant access to high-performance models—no queues, no GPUs to reserve.
Just straightforward model options you can build on.
Kimi-K2-Instruct
Kimi K2 is a mixture-of-experts (MoE) language model with 1 trillion total parameters. Kimi K2 excels at knowledge, reasoning, and coding tasks, with strong agentic capabilities.
DeepSeek-R1-0528
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.
Llama-4-Maverick-17B-128E-Instruct
Maverick beats GPT‑4o on coding, vision, reasoning and remains lightweight for efficient local deployment.
DeepSeek-V3
Rivals closed models on math and code; open weights, vetted safety, and low pricing simplify enterprise deployment.
DeepSeek-R1
Rivals closed models on math and code; open weights, vetted safety, and low pricing simplify enterprise deployment.
Meta-Llama-3.1-70B-Instruct-FP8
Llama 3.1 70B Instruct FP8 model running on 4x RTX 4090 optimised with Pliops XDP LightningAI accelerator card
Get in Touch
We're here to support your compute and AI needs. Let us know if you're looking to:
- Find an affordable GPU provider
- Sell your compute online
- Manage on-prem infrastructure
- Build a hybrid cloud solution
- Optimize your AI deployment
Businesses of any size are welcome.
PO Box 1224, Santa Clara, CA 95052, USA
+1 (831) 534-3437