Live pricing — last refreshed May 28, 2026

Google: Nano Banana Pro (Gemini 3 Pro Image Preview) vs OpenAI: GPT-5.4 Mini

Head-to-head API pricing and cost comparison between Google’s Google: Nano Banana Pro (Gemini 3 Pro Image Preview) and OpenAI’s OpenAI: GPT-5.4 Mini. Prices auto-refresh daily from OpenRouter.

Verdict

OpenAI: GPT-5.4 Mini is 63% cheaper for input tokens; OpenAI: GPT-5.4 Mini also wins on output tokens.

Side-by-side comparison

SpecGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)OpenAI: GPT-5.4 Mini
Input price (per 1M)$2.00$0.75
Cached input (per 1M)$0.20$0.07
Output price (per 1M)$12.00$4.50
Batch input (per 1M)$0.38
Batch output (per 1M)$2.25
Reasoning price (per 1M)$12.00
Context window66K400K
Vision supportYesYes
Caching supportYesYes
Batch APINoYes
Reasoning capabilityYesNo

Monthly cost at volume

Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).

VolumeGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)OpenAI: GPT-5.4 MiniSavings
1K req/day
500in / 200out tokens
$102.00$38.25$63.75
OpenAI: GPT-5.4 Mini wins
10K req/day
1500in / 500out tokens
$2,700$1,013$1,688
OpenAI: GPT-5.4 Mini wins
100K req/day
3000in / 800out tokens
$46,800$17,550$29,250
OpenAI: GPT-5.4 Mini wins
1M req/day
8000in / 2000out tokens
$1,200,000$450,000$750,000
OpenAI: GPT-5.4 Mini wins
Open in interactive calculator →

Adjust input/output token counts, request volume, batch & cached pricing.

Related comparisons

Frequently asked questions

Which is cheaper, Google: Nano Banana Pro (Gemini 3 Pro Image Preview) or OpenAI: GPT-5.4 Mini?

For input tokens, OpenAI: GPT-5.4 Mini is roughly 63% cheaper at $0.75/1M vs $2.00/1M. For output tokens, OpenAI: GPT-5.4 Mini wins at $4.50/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.

What’s the context window difference?

Google: Nano Banana Pro (Gemini 3 Pro Image Preview) has a context window of 66K tokens. OpenAI: GPT-5.4 Mini offers 400K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.

Should I use Google: Nano Banana Pro (Gemini 3 Pro Image Preview) or OpenAI: GPT-5.4 Mini?

Choose Google: Nano Banana Pro (Gemini 3 Pro Image Preview) if you’re already on the Google stack, want reasoning capabilities, or prefer its feature set. Choose OpenAI: GPT-5.4 Mini for OpenAI’s ecosystem, native vision input, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.

How are these prices kept current?

Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: May 28, 2026.