Gemini API pricing
Gemini Cost Calculator
Estimate monthly Google Gemini API spend from model choice, request volume, input and output tokens, context cache hits, Batch API pricing, storage, and grounding.
Estimate Gemini API cost
Token spend
Estimate input, output, and effective input price across Gemini text models.
Context cache hits
Model implicit cache savings and optional explicit cache storage MTok-hours.
Search costs
Add billable Google Search grounding prompts after your free monthly allowance.
How Gemini API cost is calculated
Monthly cost is estimated from input tokens, cached input tokens, output tokens, optional cache storage, and optional grounding prompts. Batch API mode applies a simple 50% token-cost reduction assumption.
Formula: input + cached input + output + cache storage + grounding. The final budget adds your selected buffer percentage.
| Planning question | Use this input | Related page |
|---|---|---|
| How does Gemini compare with OpenAI or Claude? | Use the cross-provider LLM calculator. | LLM Cost Calculator |
| How much does caching help? | Adjust context cache hit percent and storage MTok-hours. | Prompt Caching Savings Calculator |
| How many tokens are in my text? | Estimate prompt size before setting the input token field. | Token Counter |
FAQ
Does Gemini context caching require setup?
Gemini documentation says implicit caching is enabled by default for Gemini 2.5 and newer models, and cache hits are reported in usage metadata.
Why include grounding cost?
Gemini requests that use Google Search grounding can create separate billable search queries after the free monthly allowance.
Sources
Gemini prices in this site were last checked on 2026-07-02. Pricing, free allowances, and model availability can change.