Skip to main content
Version: 2026 R1

OpenAI

OpenAI offers GPT models - the most recognizable and widely used language models in the world. They are characterized by high-quality responses, excellent context understanding, and broad community support.

When to choose OpenAI​

Highest quality responses:

  • Tasks requiring precise reasoning
  • Complex analysis and inference
  • Creative content generation

Simplest configuration:

  • Only one API key needed
  • No infrastructure requirements (bucket, service account)
  • Quick setup in minutes

Proven solution:

  • Richest documentation and examples
  • Large community and support
  • Regular model updates

Function calling:

  • Excellent support for function calling
  • Integration with external tools
  • Structured JSON responses

Requirements​

  • OpenAI account
  • OpenAI API key

Step 1: Get API key​

  1. Log in to OpenAI Platform
  2. Go to API Keys
  3. Click Create new secret key
  4. Assign a name (e.g., aiproxy-key)
  5. Copy the key (starts with sk-)
Important

API key is displayed only once - save it in a secure place!

Step 2: AI Proxy Configuration​

Example aiconfiguration.json​

{
  "ProviderConnections": [
    {
      "Id": "openai-connection",
      "DisplayName": "OpenAI",
      "Type": "OpenAi",
      "ApiUrl": "https://api.openai.com/v1",
      "ApiKey": "sk-your-openai-api-key-here"
    }
  ],
  "ProviderModels": [
    {
      "Name": "gpt-4o-mini",
      "ConnectionId": "openai-connection",
      "ModelName": "gpt-4o-mini"
    },
    {
      "Name": "gpt-4o",
      "ConnectionId": "openai-connection",
      "ModelName": "gpt-4o"
    }
  ],
  "MethodTypesConfiguration": {
    "Chat": {
      "DefaultModel": "gpt-4o-mini"
    },
    "Image": {
      "DefaultModel": "gpt-4o"
    }
  }
}

Plik docker-compose.yml​

name: aiproxy_containers
services:
  ai-proxy:
    image: webconbps/aiproxy:1.0.0.235
    container_name: ai-proxy
    restart: unless-stopped
    ports:
      - "5298:8080"
      - "7033:8081"
    environment:
    # AiProxy variables
      - ASPNETCORE_ENVIRONMENT=Production
      - AppConfiguration__SelfHosted__Certificate__Path=/app/https/certificate.pem
      - AppConfiguration__SelfHosted__Certificate__Password=

    # Logging
      - Logging__LogLevel__Default=Information
      - Logging__LogLevel__Microsoft=Warning
    volumes:
      - ./certificates/certificate.pem:/app/https/certificate.pem:ro
      - ./aiconfiguration.json:/app/aiconfiguration.json:ro

Troubleshooting​

Error 401 Unauthorized​

  • Check if API key is correct
  • Make sure the key hasn't expired

Error 429 Rate Limit​

  • Check your OpenAI account limits
  • Analyze request frequency

Error "Model not found"​

  • Check if model name is correct
  • Make sure you have access to the given model

Chat and Vision Models​

  • gpt-4o - multimodal next-generation model (text, image support)
  • gpt-4o-mini - more efficient version of gpt-4o (lower costs)
  • o1-preview - model with advanced reasoning
  • o1-mini - model for tasks requiring precise thinking
  • gpt-4-turbo - faster GPT-4 with larger context
Note

OpenAI models are regularly updated. The latest versions (like gpt-4o-2024-11-20) are available in the OpenAI Models documentation.

Embedding Models​

  • text-embedding-3-small - compact embeddings
  • text-embedding-3-large - high-quality embeddings
  • text-embedding-ada-002 - older standard

Further resources​