Proxed.AI

GPT‑5 Support + New Image Generation API

We shipped two big updates:

#
GPT‑5 support

  • New models: gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat-latest
  • Pricing integrated in calculators and estimates
  • Backwards compatible; no SDK changes required

Usage:

await fetch(`https://api.proxed.ai/v1/openai/${PROJECT_ID}/chat/completions`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${PARTIAL_KEY}.${DEVICE_TOKEN}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-5",
    messages: [{ role: "user", content: "Give me a concise plan." }],
  }),
});

See the full post: /updates/gpt-5-is-here

#
Image Generation API (Experimental)

  • Endpoint: POST /v1/image (or /v1/image/{projectId})
  • Providers: OpenAI (gpt-image-1, dall-e-3, dall-e-2), Google (imagen-3.0-generate-002)
  • Supports size/aspectRatio, n, seed, and provider-specific options

Quick start:

curl -X POST \
  https://api.proxed.ai/v1/image/{your-project-id} \
  -H "Authorization: Bearer {your-partial-api-key}.{your-device-token-or-test-key}" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A retro-futuristic city skyline at dusk",
    "model": "gpt-image-1",
    "size": "1024x1024"
  }'

See the full post: /updates/image-generation

#
Security hardening (dashboard)

We tightened response headers in the dashboard app to align with OWASP Secure Headers:

  • Cross-Origin-Opener-Policy: same-origin
  • Cross-Origin-Resource-Policy: same-origin
  • Strict-Transport-Security: max-age=63072000; includeSubDomains; preload
  • X-Content-Type-Options: nosniff
  • Referrer-Policy: strict-origin-when-cross-origin
  • X-Frame-Options: DENY
  • Permissions-Policy: restricted sensitive features
  • CSP refined with stricter sources and upgrade-insecure-requests

These changes improve isolation, reduce data leakage, and prevent common classes of attacks without impacting normal functionality.