Low Cost X‑Serve™ Inference
Powered by X‑Mem™

Netpreme’s X-Serve™ is an inference cloud for open models and coding agents, backed by an inference stack optimized for each model architecture, with a drop-in OpenAI-compatible API.Netpreme’s X-Serve™ is an inference cloud for open models and coding agents, with a drop-in OpenAI-compatible API.

Try for Free Read the Docs

API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.netpreme.com/v1",
    api_key="NETPREME_API_KEY",
)

response = client.chat.completions.create(
    model="moonshotai/Kimi-K3",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "In one sentence, what can you help me with?"},
    ],
)

print(response.choices[0].message.content)

Coding Agents

export ANTHROPIC_AUTH_TOKEN="NETPREME_API_KEY"

export ANTHROPIC_BASE_URL=https://api.netpreme.com
export ANTHROPIC_MODEL=moonshotai/Kimi-K3
export ANTHROPIC_DEFAULT_HAIKU_MODEL=moonshotai/Kimi-K3
export CLAUDE_CODE_MAX_CONTEXT_TOKENS=512000
export CLAUDE_CODE_MAX_OUTPUT_TOKENS=128000
export CLAUDE_CODE_AUTO_COMPACT_WINDOW=409600

claude

Low Cost X‑Serve™ InferencePowered by X‑Mem™

Low Cost X‑Serve™ Inference
Powered by X‑Mem™