LLM Gateway Authentication with Your APIXO API Key - APIXO

LLM Gateway requests use your APIXO API key. The header name follows the compatible provider API so existing SDKs and tools can keep their normal request format. Create a key in the APIXO dashboard, then store it as APIXO_API_KEY.

export APIXO_API_KEY="your_apixo_api_key"

Header by API format

Compatible API	Header
Claude API	`x-api-key: $APIXO_API_KEY`
OpenAI Responses API	`Authorization: Bearer $APIXO_API_KEY`
Gemini API	`x-goog-api-key: $APIXO_API_KEY`

Claude required version header

Claude-compatible requests also require the Anthropic protocol version header. Most Claude SDKs add this automatically.

anthropic-version: 2023-06-01

Example

curl -X POST "https://llm.apixo.ai/v1/messages" \
  -H "x-api-key: $APIXO_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 128,
    "messages": [{"role": "user", "content": "Say hello."}]
  }'

Do not expose APIXO keys in browser-side code. Make LLM Gateway calls from your backend, serverless function, or trusted runtime.

Security best practices

Environment variables: Store your keys securely as environment variables (APIXO_API_KEY) rather than hardcoding credentials into application source code.
Backend isolation: Keep all LLM Gateway calls inside server-side environments or trusted serverless functions. Never expose raw keys in client-side web apps or mobile binaries.