GPT-4o Mini: Pricing, Context, and Benchmarks

GPT-4o Mini is OpenAI's GPT-4 model released on 2024-07-18. It runs on a 128K-token context window, priced at $0.15/M input and $0.60/M output. Affordable small model for high-volume tasks. Replaces GPT-3.5 in the API.

Specifications

What this model is good for

Based on benchmark scores and capability fit, GPT-4o Mini ranks well for:

• Cheapest Model with Vision — rank #2. $0.15/M input + full vision capability. The standard cheap-vision pick.

Cost calculator

For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0008 per call. For typical usage:

For more precise estimates including caching discounts, use the LLM API Cost Calculator.

Other OpenAI models

• GPT-5
• GPT-5 Mini
• GPT-5 Nano
• o3
• GPT-4.1
• o3-mini

Common comparisons

• GPT-4o Mini vs Codestral Side-by-side specs, pricing, and benchmarks
• GPT-4o Mini vs DeepSeek-V3 Side-by-side specs, pricing, and benchmarks
• GPT-4o Mini vs Gemini 2.5 Flash Side-by-side specs, pricing, and benchmarks
• GPT-4o Mini vs Qwen3-235B Side-by-side specs, pricing, and benchmarks

API setup

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello"}]}'

See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.