GPT-4o vs Gemini 2.5 Flash

Pricing as of 2026-06-26

GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output, versus $0.15 and $0.6 for Gemini 2.5 Flash. For a 1M-input + 1M-output workload, Gemini 2.5 Flash is cheaper — about $0.75 vs $12.50. Gemini 2.5 Flash has the larger context window (1,048,576 vs 128,000 tokens).

Prices are list prices per 1,000,000 tokens, sourced from each provider and stored in Tokenia's model dataset. Estimates exclude caching, batch and volume discounts. Always confirm current pricing with the provider.