Model comparison

GPT-5.4 Mini vs Gemini 2.5 Flash Cost Calculator

GPT-5.4 Mini

$0.75/M input

$4.5/M output

$0.075/M cached input

Lower-cost OpenAI model seed.

$0.3/M input

$2.5/M output

$0.03/M cached input

Fast Gemini text seed with thinking included in output.

Quick estimate

No API key needed. Pick a model, paste your question, choose the answer length, and get a close cost estimate.

1. Choose AI model

$0.75/M input$4.5/M output200,000 ctxCache pricingBatchFlexPriority

2. Your question or prompt

3. How long will the AI answer be?

Optional: paste the AI answer if you already have it

Your estimate will appear here.

Paste a prompt, choose an answer length, and calculate.

GPT-5.4 Mini: $0.003000

Gemini 2.5 Flash: $0.001550

GPT-5.4 Mini: $0.0413

Gemini 2.5 Flash: $0.0200

GPT-5.4 Mini: $0.0165

Gemini 2.5 Flash: $0.008000

Which is cheaper, GPT-5.4 Mini or Gemini 2.5 Flash?

Gemini 2.5 Flash has the lower combined input plus output seed rate for this comparison.

Why might my bill differ from this comparison?

Cache usage, tools, search, long-context tiers, region multipliers, and provider-reported token counts can change the final bill.