Skip to content

Meet DeepintShield at Bengaluru Tech Summit 2026, 17 to 19 November, BIEC Hall 1, booth H1A106. Book 20 minutes

Start For Free

OpenAI

GPT chat, Responses, embeddings, images, audio, video, files and batch.

OpenAI is the baseline schema for the DeepintShield gateway. Use your own OpenAI project key and route GPT models through one governed endpoint.

What works

  • Chat Completions and the Responses API, including the stored Responses lifecycle and compaction
  • Legacy text completions, embeddings, speech (TTS) and transcription (STT)
  • Image generation, edit and variation; video generation; files, batch and list models
  • Streaming for chat, Responses, text, TTS and STT, plus partial images for image generation and edit
  • Tools, structured output and reasoning; Realtime WebSocket relay and WebRTC SDP control passthrough

Limits to know: Image variation does not stream. max_completion_tokens has a minimum of 16. Provider prompt caching is automatic for OpenAI.

How to connect

Add your OpenAI project key in Model Hub → AI Providers, create a Virtual Key, then call openai/<model> through https://app.deepintshield.com/v1 with any OpenAI-compatible client.

Read the OpenAI provider docs. Requests get the same Virtual Key budgets, guardrails and logs as every other provider on the AI gateway.

Read the integration docs

Start For Free