Serve models like Llama 4 and DeepSeek 3.1 with our high-performance GPU platform. Our Inference APIs make it simple to scale your projects and pay only for what you need.
Rivals closed models on math and code; open weights, vetted safety, and low pricing simplify enterprise deployment.
Get API KeyKimi 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.
Get API KeyMay 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.
Get API Keyimport 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);
}Models
Cost-effective access to high-performance models — no queues, no GPUs to reserve. Just straightforward model options you can build on.
Rivals closed models on math and code; open weights, vetted safety, and low pricing simplify enterprise deployment.
Get API KeyKimi 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.
Get API KeyMay 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.
Get API KeyRivals closed models on math and code; open weights, vetted safety, and low pricing simplify enterprise deployment.
Get API KeyGet in touch with our team to discuss your requirements and find the right solution for your infrastructure.