Live pricing — last refreshed Apr 21, 2026

Anthropic: Claude Haiku 4.5 vs Google: Gemini 2.5 Pro Preview 06-05

Head-to-head API pricing and cost comparison between Anthropic’s Anthropic: Claude Haiku 4.5 and Google’s Google: Gemini 2.5 Pro Preview 06-05. Prices auto-refresh daily from OpenRouter.

Verdict

Anthropic: Claude Haiku 4.5 is 20% cheaper for input tokens; Anthropic: Claude Haiku 4.5 also wins on output tokens.

Side-by-side comparison

SpecAnthropic: Claude Haiku 4.5Google: Gemini 2.5 Pro Preview 06-05
Input price (per 1M)$1.00$1.25
Cached input (per 1M)$0.10$0.13
Output price (per 1M)$5.00$10.00
Batch input (per 1M)$0.50
Batch output (per 1M)$2.50
Reasoning price (per 1M)$10.00
Context window200K1049K
Vision supportYesYes
Caching supportYesYes
Batch APIYesNo
Reasoning capabilityNoYes

Monthly cost at volume

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

VolumeAnthropic: Claude Haiku 4.5Google: Gemini 2.5 Pro Preview 06-05Savings
1K req/day
500in / 200out tokens
$45.00$78.75$33.75
Anthropic: Claude Haiku 4.5 wins
10K req/day
1500in / 500out tokens
$1,200$2,063$862.50
Anthropic: Claude Haiku 4.5 wins
100K req/day
3000in / 800out tokens
$21,000$35,250$14,250
Anthropic: Claude Haiku 4.5 wins
1M req/day
8000in / 2000out tokens
$540,000$900,000$360,000
Anthropic: Claude Haiku 4.5 wins
Open in interactive calculator →

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

Related comparisons

Frequently asked questions

Which is cheaper, Anthropic: Claude Haiku 4.5 or Google: Gemini 2.5 Pro Preview 06-05?

For input tokens, Anthropic: Claude Haiku 4.5 is roughly 20% cheaper at $1.00/1M vs $1.25/1M. For output tokens, Anthropic: Claude Haiku 4.5 wins at $5.00/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.

What’s the context window difference?

Anthropic: Claude Haiku 4.5 has a context window of 200K tokens. Google: Gemini 2.5 Pro Preview 06-05 offers 1049K 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 Anthropic: Claude Haiku 4.5 or Google: Gemini 2.5 Pro Preview 06-05?

Choose Anthropic: Claude Haiku 4.5 if you’re already on the Anthropic stack, want broad ecosystem support, or prefer its lower input price. Choose Google: Gemini 2.5 Pro Preview 06-05 for Google’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.