Confidential AI API

curl https://api.voltagegpu.com/v1/confidential/chat/completions \
  -H "Authorization: Bearer vgpu_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "contract-analyst",
    "messages": [
      {"role": "user", "content": "Review this NDA clause: The Receiving Party shall not disclose any Confidential Information for 5 years..."}
    ],
    "max_tokens": 2048,
    "stream": true
  }'

from openai import OpenAI

# One line to change, same SDK, same code.
# Requests pass through our relay, which sees them in clear (TLS ends at our host).
# To keep plaintext off our servers, run your own inference server in a
# Confidential VM and terminate TLS inside its trust domain.
client = OpenAI(
    base_url="https://api.voltagegpu.com/v1/confidential",
    api_key="vgpu_YOUR_API_KEY",
)

# Use any of the 9 agents as model ID
response = client.chat.completions.create(
    model="contract-analyst",  # or: financial-analyst, compliance-officer, etc.
    messages=[
        {"role": "user", "content": "Review this NDA and flag non-standard terms:\n\n" + nda_text}
    ],
    max_tokens=2048,
)

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

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.voltagegpu.com/v1/confidential',
  apiKey: 'vgpu_YOUR_API_KEY',
});

const response = await client.chat.completions.create({
  model: 'financial-analyst',
  messages: [
    { role: 'user', content: 'Analyze this P&L for red flags:\n\n' + financialData }
  ],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.voltagegpu.com/v1/confidential",
    api_key="vgpu_YOUR_API_KEY",
    model="compliance-officer",
)

response = llm.invoke("Assess GDPR compliance gaps in our AI usage policy")
print(response.content)

Authorization: Bearer vgpu_YOUR_API_KEY