OpenAI API Pricing 2026: GPT-5, O1, O3 Cost Comparison (February 2026)

OpenAI API pricing 2026: GPT-5, O1, O3, GPT-4o cost per million tokens. Includes input/output pricing, context limits, and how to optimize costs.

OpenAI API Pricing 2026

TL;DR — OpenAI API Prices (Feb 2026)

  • GPT-5: $1.25/$10.00 per 1M input/output tokens
  • GPT-4.1: $2.00/$8.00 per 1M tokens
  • GPT-4o Mini: $0.15/$0.60 per 1M tokens
  • O1 (Reasoning): $15.00/$60.00 per 1M tokens
  • O3 (Advanced): $2.00/$8.00 per 1M tokens

OpenAI offers the widest range of models from cheap fast models to expensive reasoning powerhouses.


GPT-5 Family (Flagship)

Model Context Input / 1M tokens Output / 1M tokens
GPT-5.2 Pro 400K $21.00 $168.00
GPT-5.1 400K $10.00 $80.00
GPT-5 400K $1.25 $10.00
GPT-5 Mini 400K $0.25 $2.00
GPT-5 Nano 400K $0.05 $0.40

O-Series (Reasoning)

Model Context Input / 1M tokens Output / 1M tokens
O3 Pro 200K $150.00 $600.00
O1 200K $15.00 $60.00
O1 Mini 200K $1.10 $4.40

GPT-4 Family

Model Context Input / 1M tokens Output / 1M tokens
GPT-4.1 1M $2.00 $8.00
GPT-4.1 Mini 1M $0.40 $1.60
GPT-4.1 Nano 1M $0.10 $0.40
GPT-4o 128K $2.50 $10.00
GPT-4o Mini 128K $0.15 $0.60

Cost Optimization Tips

  1. Use Mini models for simple tasks - 10-50x cheaper
  2. Prompt caching - 50-90% off for repeated context
  3. Batch API - 50% off for async processing
  4. Choose the right model - Don't use O1 for simple queries

Related

Want more resources?

Subscribe to get the latest AI tools, guides, and updates.

Newsletter

Stay ahead of the curve

Key insights from top tech podcasts, delivered daily. Join 10,000+ engineers, founders, and investors.

One email per day. Unsubscribe anytime.