How much does the Gemini API cost?

Gemini pricing runs from $0.075 to $3.50 per 1M input tokens depending on the model. Gemini 3.5 Live Translate costs $3.50 per 1M input and $21.00 per 1M output tokens.

What is the cheapest Gemini model?

Gemini 2.0 Flash-Lite is the cheapest Gemini model we track, at $0.075 per 1M input tokens and $0.300 per 1M output tokens.

Does Gemini charge less for cached tokens?

Yes. Cached input is billed at a lower rate than fresh input — for Gemini 3.6 Flash it is $0.150 per 1M versus $1.50, about 90% cheaper. Caching applies to repeated prompt prefixes.

How often is this Gemini pricing updated?

Every day. Prices are read directly from the published pricing page, normalized to USD per 1,000,000 tokens, and only recorded when a number actually changes — so the history shows real price movements rather than daily noise.

Gemini API pricing

Every Gemini model from Google we track, with input, cached input and output cost in USD per 1M tokens. Google publishes a free tier alongside paid pricing, and several Gemini models charge a higher rate above a long-context threshold.

29 models · updated 2026-08-11 · prices in USD per 1,000,000 tokens

Models tracked

$0.075

Cheapest input — Gemini 2.0 Flash-Lite

$3.50

Priciest input — Gemini 3.5 Live Translate

Largest context — Gemini 3.6 Flash

Listed in the order Google publishes them.

Gemini models with input, cached input and output pricing per million tokens

Gemini 3.6 Flash	$1.50	$0.150	$7.50	1M
Gemini 3.5 Flash	$1.50	$0.150	$9.00	1M
Gemini 3.5 Live Translate	$3.50	—	$21.00	—
Gemini 3.5 Flash-Lite	$0.300	$0.030	$2.50	1M
Gemini 3.1 Flash-Lite	$0.250	$0.025	$1.50	1M
Gemini Omni Flash Preview	$1.50	—	$9.00	—
Gemini 3.1 Pro Preview	$2.00	$0.200	$12.00	1M
Gemini 3.1 Flash Live Preview	$0.750	—	$4.50	—
Gemini 3.1 Flash Image (Nano Banana 2) 🍌	$0.500	—	$3.00	131K
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 🍌	$0.250	—	$1.50	66K
Gemini 3.1 Flash TTS Preview	$1.00	—	$20.00	—
Gemini 3 Flash Preview	$0.500	$0.050	$3.00	1M
Gemini 3 Pro Image (Nano Banana Pro) 🍌	$2.00	—	$12.00	131K
Gemini 2.5 Pro	$1.25	$0.125	$10.00	1M
Gemini 2.5 Flash	$0.300	$0.030	$2.50	1M
Gemini 2.5 Flash-Lite	$0.100	$0.010	$0.400	1M
Gemini 2.5 Flash-Lite Preview	$0.100	$0.010	$0.400	—
Gemini 2.5 Flash Native Audio (Live API)	$0.500	—	$2.00	—
Gemini 2.5 Flash Image (Nano Banana) 🍌	$0.300	—	$0.039	33K
Gemini 2.5 Flash Preview TTS	$0.500	—	$10.00	—
Gemini 2.5 Pro Preview TTS	$1.00	—	$20.00	—
Gemini 2.0 Flash	$0.100	$0.025	$0.400	—
Gemini 2.0 Flash-Lite	$0.075	—	$0.300	—
Gemini Embedding 2	$0.200	—	—	—
Gemini Embedding	$0.150	—	—	—
Gemini Robotics ER 2 Preview	$2.00	$0.200	$10.00	—
Gemini Robotics ER 2 Streaming Preview	$2.00	—	$10.00	—
Gemini Robotics ER 1.6 Preview	$1.00	—	$5.00	—
Gemini 2.5 Computer Use Preview	$1.25	—	$10.00	—

Gemini pricing questions

How much does the Gemini API cost?: Gemini pricing runs from $0.075 to $3.50 per 1M input tokens depending on the model. Gemini 3.5 Live Translate costs $3.50 per 1M input and $21.00 per 1M output tokens.
What is the cheapest Gemini model?: Gemini 2.0 Flash-Lite is the cheapest Gemini model we track, at $0.075 per 1M input tokens and $0.300 per 1M output tokens.
Does Gemini charge less for cached tokens?: Yes. Cached input is billed at a lower rate than fresh input — for Gemini 3.6 Flash it is $0.150 per 1M versus $1.50, about 90% cheaper. Caching applies to repeated prompt prefixes.
How often is this Gemini pricing updated?: Every day. Prices are read directly from the published pricing page, normalized to USD per 1,000,000 tokens, and only recorded when a number actually changes — so the history shows real price movements rather than daily noise.

Gemini pricing questions

Compare with other providers