TokenTally

Google DeepMind

Gemini Flash pricing

Flash delivers a million-token context for pennies. Model newsletter bots, content moderators, and QA helpers here.

Last pricing check: Mar 13, 2026

$0.35 per 1M prompt tokens$1.05 per 1M completion tokens1,000,000 token context

Why teams choose this model

Content moderation
Newsletter + blog drafting
Product QA assistants
Open main calculator

Scenario planning

Realistic cost examples

Numbers use Gemini 1.5 Flash pricing

Content guardrails

Flag tone, compliance, or toxicity before publishing user copy.

Per request

$0.0004

Per month

$24.36

Tokens sent

43,200,000

500 prompt tokens220 completion tokens60,000 requests/mo

Newsletter bot

Weekly digests sourced from product + community updates.

Per request

$0.0012

Per month

$1.84

Tokens sent

2,850,000

1100 prompt tokens800 completion tokens1,500 requests/mo

QA helper

Docs-aware assistant answering product questions inside the app.

Per request

$0.0006

Per month

$5.51

Tokens sent

9,450,000

700 prompt tokens350 completion tokens9,000 requests/mo

Compare with

Google

Gemini 1.5 Pro Pricing Guide

Updated Mar 13, 2026

Google

Gemini 2.5 Flash-Lite Pricing

Updated Mar 13, 2026

Google

Gemini 3.1 Flash-Lite Preview Pricing

Updated Mar 13, 2026

FAQs

When should I choose Flash over Pro?

Pick Flash when latency + price matter more than maximum reasoning depth. It’s ideal for moderation, summarization, and FAQ-style bots.

Does Flash support tool use?

Yes, and you only pay for the tokens consumed invoking those tools.

Is there a tokens-per-minute quota?

Google enforces TPM caps per project. Model your peak usage in TokenTally to stay within those guardrails.

Pricing sources