AI & LLM Providers

​

OpenAI

• GPT-5 - State-of-the-art coding & agents (74.9% SWE-bench, 88% Aider)
• GPT-5 Mini - Balanced performance & cost
• GPT-5 Nano - Ultra-fast & affordable
• GPT-5 Pro - Highest quality with scaled reasoning
• o3 - Advanced reasoning model
• DALL-E 3 - Image generation
• Whisper - Speech-to-text

• GPT-5: $1.25 input /$10 output
• GPT-5 Mini: $0.25 input /$2 output
• GPT-5 Nano: $0.05 input /$0.40 output
• Prompt caching: $0.125/1M tokens

• 45% fewer factual errors with web search
• 80% fewer hallucinations vs o3
• 4 reasoning levels: minimal, low, medium, high
• Parallel & sequential tool calling
• Available to free users

• Direct database access
• Global deployment
• TypeScript/JavaScript
• Built-in secrets management
• Free tier included

• Deno runtime only
• Supabase ecosystem

// Supabase Edge Function example
import { serve } from "https://deno.land/[email protected]/http/server.ts"

serve(async (req) => {
  const { prompt } = await req.json()

  const response = await fetch("https://api.openai.com/v1/chat/completions", {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${Deno.env.get("OPENAI_API_KEY")}`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "gpt-4",
      messages: [{ role: "user", content: prompt }]
    })
  })

  return new Response(JSON.stringify(await response.json()))
})