// Base API URL

https://api.openai.com/

gpt-5-nano-2025-08-07

// Model Details

  • Use Case: Ultra-low latency, speed-critical tasks.
  • Context: 128,000 tokens
  • Max Output: 32,000 tokens

// Pricing (per 1M)

  • Input: $0.05
  • Output: $0.50

// API Endpoints

  • v1/chat/completions
  • v1/responses
  • v1/embeddings
  • v1/moderations

gpt-5-mini-2025-08-07

// Model Details

  • Use Case: Balanced speed, cost, and performance.
  • Context: 400,000 tokens
  • Max Output: 128,000 tokens

// Pricing (per 1M)

  • Input: $0.25
  • Output: $2.00

// API Endpoints

  • v1/chat/completions
  • v1/responses
  • v1/realtime
  • v1/batch
  • v1/embeddings
  • v1/audio/speech
  • v1/audio/transcriptions
  • v1/moderations

gpt-5-2025-08-07

// Model Details

  • Use Case: Max power for reasoning, coding, agents.
  • Context: 400,000 tokens
  • Max Output: 128,000 tokens

// Pricing (per 1M)

  • Input: $1.25
  • Output: $10.00

// API Endpoints

  • v1/chat/completions
  • v1/responses
  • v1/realtime
  • v1/assistants
  • v1/batch
  • v1/fine-tuning
  • v1/embeddings
  • v1/images/generations
  • v1/images/edits
  • v1/audio/speech
  • v1/audio/transcriptions
  • v1/audio/translations
  • v1/moderations
  • v1/completions (legacy)