LLMCostLab

PricesCompare → Claude Sonnet 5 vs Gemini 3.7 Flash

Claude Sonnet 5 vs Gemini 3.7 Flash: API cost compared

Claude Sonnet 5 lists at $2.000 in / $10.00 out per 1M tokens. Gemini 3.7 Flash lists at $0.750 in / $3.750. Sticker price only tells you so much — below is what each actually costs across eight production workloads.

advertisement
Cheaper on more workloads
Gemini 3.7 Flash
wins 8 of 8
Blended rate gap
2.7x
at 3:1 in:out

Side by side

Claude Sonnet 5Gemini 3.7 Flash
ProviderAnthropicGoogle
Input per 1M$2.000$0.750
Output per 1M$10.00$3.750
Cached input per 1M$0.200not published
Context window200k1M
Blended per 1M (3:1)$4.000$1.500

Monthly cost by workload

Caching applied at each workload's typical hit rate. This is where the two models actually separate.

WorkloadClaude Sonnet 5Gemini 3.7 FlashCheaperDifference
Customer support chatbot$257.80$133.12Gemini 3.7 Flash$124.68 (48%)
RAG document Q&A$368.00$165.00Gemini 3.7 Flash$203.00 (55%)
Coding agent$185.00$120.00Gemini 3.7 Flash$65.00 (35%)
Bulk summarization$2,692$1,050Gemini 3.7 Flash$1,642 (61%)
Structured data extraction$3,490$1,781Gemini 3.7 Flash$1,709 (49%)
Long-form content generation$429.20$165.00Gemini 3.7 Flash$264.20 (62%)
Email triage agent$805.00$487.50Gemini 3.7 Flash$317.50 (39%)
Translation pipeline$2,810$1,069Gemini 3.7 Flash$1,741 (62%)
advertisement

How to read this

Gemini 3.7 Flash is cheaper on the majority of these workloads, but "majority" is not the decision. The output:input price ratio is 5.0 for Claude Sonnet 5 and 5.0 for Gemini 3.7 Flash. If your traffic is output-heavy — long-form drafting, translation — the model with the lower output price wins regardless of what the input price suggests. If you are input-heavy — RAG, bulk summarization, agents re-reading a codebase — the cached input rate matters more than either headline number.

Cost is also not the only axis. This site does not benchmark quality, latency, or rate limits, and a model that is 3x cheaper but needs two attempts per task is not cheaper. Use these numbers to size a bill, then validate on your own evals.

Run your own numbers

Cost calculator

Enter your own numbers, or start from a workload preset. Costs are monthly and update as you type.

Cheapest model
Cheapest → priciest spread
ModelIn /1MOut /1MMonthlyvs best