Live pricing — last refreshed Apr 21, 2026

Anthropic: Claude Sonnet 4.6 vs Google: Gemini 2.5 Flash Lite Preview 09-2025

Head-to-head API pricing and cost comparison between Anthropic’s Anthropic: Claude Sonnet 4.6 and Google’s Google: Gemini 2.5 Flash Lite Preview 09-2025. Prices auto-refresh daily from OpenRouter.

Verdict

Google: Gemini 2.5 Flash Lite Preview 09-2025 is 97% cheaper for input tokens; Google: Gemini 2.5 Flash Lite Preview 09-2025 also wins on output tokens.

Side-by-side comparison

SpecAnthropic: Claude Sonnet 4.6Google: Gemini 2.5 Flash Lite Preview 09-2025
Input price (per 1M)$3.00$0.10
Cached input (per 1M)$0.30$0.01
Output price (per 1M)$15.00$0.40
Batch input (per 1M)$1.50
Batch output (per 1M)$7.50
Reasoning price (per 1M)$0.40
Context window1000K1049K
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 Sonnet 4.6Google: Gemini 2.5 Flash Lite Preview 09-2025Savings
1K req/day
500in / 200out tokens
$135.00$3.90$131.10
Google: Gemini 2.5 Flash Lite Preview 09-2025 wins
10K req/day
1500in / 500out tokens
$3,600$105.00$3,495
Google: Gemini 2.5 Flash Lite Preview 09-2025 wins
100K req/day
3000in / 800out tokens
$63,000$1,860$61,140
Google: Gemini 2.5 Flash Lite Preview 09-2025 wins
1M req/day
8000in / 2000out tokens
$1,620,000$48,000$1,572,000
Google: Gemini 2.5 Flash Lite Preview 09-2025 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 Sonnet 4.6 or Google: Gemini 2.5 Flash Lite Preview 09-2025?

For input tokens, Google: Gemini 2.5 Flash Lite Preview 09-2025 is roughly 97% cheaper at $0.10/1M vs $3.00/1M. For output tokens, Google: Gemini 2.5 Flash Lite Preview 09-2025 wins at $0.40/1M. 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 Sonnet 4.6 has a context window of 1000K tokens. Google: Gemini 2.5 Flash Lite Preview 09-2025 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 Sonnet 4.6 or Google: Gemini 2.5 Flash Lite Preview 09-2025?

Choose Anthropic: Claude Sonnet 4.6 if you’re already on the Anthropic stack, want broad ecosystem support, or prefer its feature set. Choose Google: Gemini 2.5 Flash Lite Preview 09-2025 for Google’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: Apr 21, 2026.