Documentation

Quick start

Get Proxide working in under 2 minutes. You only need to change your baseURL — everything else stays the same.

Step 1: Sign up and get your API key

Create an account at app.proxide.ai. After signing up, navigate to Settings → API Keys and create a new key. Your Proxide API key starts with prox-.

You'll also need to add your provider API keys (OpenAI, Anthropic, etc.) in Settings → Provider Keys. Proxide uses your own keys — there's no per-token markup.

Step 2: Change your baseURL

Replace your existing API key with your Proxide key, and point your client at the Proxide gateway. Every other line of your code stays unchanged.

TypeScript / JavaScript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "prox-your-key-here",         // Your Proxide key
  baseURL: "https://gateway.proxide.ai/openai/v1",
});

// All existing calls work unchanged
const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});
Python
from openai import OpenAI

client = OpenAI(
    api_key="prox-your-key-here",        # Your Proxide key
    base_url="https://gateway.proxide.ai/openai/v1",
)

# All existing calls work unchanged
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
Claude Code / claude CLI
# Set environment variables for Claude Code
export ANTHROPIC_API_KEY="prox-your-key-here"
export ANTHROPIC_BASE_URL="https://gateway.proxide.ai/anthropic/v1"

# Now run claude as normal — all requests go through Proxide
claude "Help me refactor this function"
curl
curl https://gateway.proxide.ai/openai/v1/chat/completions \
  -H "Authorization: Bearer prox-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Step 3: Verify it's working

Your response will include Proxide headers confirming the request was routed through the gateway:

Response headers
x-proxide-request-id: req_01JQK3...
x-proxide-provider: openai/gpt-4o
x-proxide-cache: miss
x-proxide-latency-ms: 423

You can also check your Proxide dashboard — the request should appear in your audit log within a few seconds.

What's next

Set budget limits →

Add x-proxide-client-id headers to track spend per agent and enforce daily/monthly limits.

Configure failover →

Set up a fallback provider chain so rate limits and outages never reach your users.

Enable PII redaction →

Turn on automatic PII stripping for GDPR and HIPAA compliance with zero code changes.

Turn on semantic cache →

Cut LLM costs 20–40% by caching responses based on semantic similarity.

Supported providers

OpenAIAnthropicGoogle GeminiGroqDeepSeekMistralTogether AIFireworks AICoherePerplexityAWS BedrockAzure OpenAI20+ more