Live pricing — last refreshed Apr 21, 2026

Google: Nano Banana (Gemini 2.5 Flash Image) vs Anthropic: Claude Haiku 4.5

Head-to-head API pricing and cost comparison between Google’s Google: Nano Banana (Gemini 2.5 Flash Image) and Anthropic’s Anthropic: Claude Haiku 4.5. Prices auto-refresh daily from OpenRouter.

Verdict

Google: Nano Banana (Gemini 2.5 Flash Image) is 70% cheaper for input tokens; Google: Nano Banana (Gemini 2.5 Flash Image) also wins on output tokens.

Side-by-side comparison

SpecGoogle: Nano Banana (Gemini 2.5 Flash Image)Anthropic: Claude Haiku 4.5
Input price (per 1M)$0.30$1.00
Cached input (per 1M)$0.03$0.10
Output price (per 1M)$2.50$5.00
Batch input (per 1M)$0.50
Batch output (per 1M)$2.50
Reasoning price (per 1M)$2.50
Context window33K200K
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 (Gemini 2.5 Flash Image)Anthropic: Claude Haiku 4.5Savings
1K req/day
500in / 200out tokens
$19.50$45.00$25.50
Google: Nano Banana (Gemini 2.5 Flash Image) wins
10K req/day
1500in / 500out tokens
$510.00$1,200$690.00
Google: Nano Banana (Gemini 2.5 Flash Image) wins
100K req/day
3000in / 800out tokens
$8,700$21,000$12,300
Google: Nano Banana (Gemini 2.5 Flash Image) wins
1M req/day
8000in / 2000out tokens
$222,000$540,000$318,000
Google: Nano Banana (Gemini 2.5 Flash Image) 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 (Gemini 2.5 Flash Image) or Anthropic: Claude Haiku 4.5?

For input tokens, Google: Nano Banana (Gemini 2.5 Flash Image) is roughly 70% cheaper at $0.30/1M vs $1.00/1M. For output tokens, Google: Nano Banana (Gemini 2.5 Flash Image) wins at $2.50/1M. 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 (Gemini 2.5 Flash Image) has a context window of 33K tokens. Anthropic: Claude Haiku 4.5 offers 200K 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 (Gemini 2.5 Flash Image) or Anthropic: Claude Haiku 4.5?

Choose Google: Nano Banana (Gemini 2.5 Flash Image) if you’re already on the Google stack, want reasoning capabilities, or prefer its lower input price. Choose Anthropic: Claude Haiku 4.5 for Anthropic’s ecosystem, native vision input, or its differentiated capabilities. 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: Apr 21, 2026.