LLM API pricing / Google

What the Gemini API costs, model by model

Short answer. Google lists 10 models with a per-token price on its API. Input: from $0.10 (Gemini 2.5 Flash-Lite) to $2.00 (Gemini 3.1 Pro Preview, Gemini 4 Argon and Gemini 4 Carbon) per 1M tokens. Output: from $0.40 (Gemini 2.5 Flash-Lite) to $12.00 (Gemini 3.1 Pro Preview). Read on Google's own pages on November 16, 2026.

In plain words. You pay for the tokens you send (input) and the tokens the model writes (output). One request of 10,000 tokens in and 1,000 out costs $0.0014 on Gemini 2.5 Flash-Lite and $0.032 on Gemini 3.1 Pro Preview. Output costs more than input on all 10 models.

Current models

10 models, cheapest input first, verified on November 16, 2026. The last column is the cost of one request of 10,000 input and 1,000 output tokens at these prices, with no cache.

ModelInput $/1MOutput $/1MCached inputContextExample requestVerified
Gemini 2.5 Flash-Lite $0.10 $0.40 $0.01 1.0M $0.0014 2026-11-16
Gemini 3.5 Flash-Lite $0.30 $2.50 $0.03 1.0M $0.0055 2026-11-16
Gemini 3.6 Flash promo $0.75 $3.75 $0.075 1.0M $0.0112 2026-11-16
Gemini 3.8 Flash promo $0.75 $3.75 $0.075 1.0M $0.0112 2026-11-16
Gemini Robotics ER 2 Preview promo $1.00 $5.00 $0.10 131K $0.015 2026-11-16
Gemini Robotics ER 2 Streaming Preview promo $1.00 $5.00 — 131K $0.015 2026-11-16
Gemini 4 Hydrogen $1.50 $7.50 $0.075 1.0M $0.0225 2026-11-16
Gemini 3.1 Pro Preview $2.00 $12.00 $0.20 1.0M $0.032 2026-11-16
Gemini 4 Argon promo $2.00 $10.00 $0.10 1.0M $0.03 2026-11-16
Gemini 4 Carbon promo $2.00 $10.00 $0.10 1.0M $0.03 2026-11-16

How Google describes its models

How Google prices its models

Second price lists

Prices Google prints for other ways of buying the same tokens, per 1M tokens, only where its page prints a figure for the model.

Batch · 50% of the standard interactive API cost

Google: "Batch API usage is priced at 50% of the standard interactive API cost for the equivalent model." source

Flex · 50% cost reduction compared to standard rates

Google: "The Gemini Flex API is an inference tier that offers a 50% cost reduction compared to standard rates, in exchange for variable latency and best-effort availability." source

Priority · no multiplier printed; the page prints the prices

Google: "The Gemini Priority API is a premium inference tier designed for business-critical workloads that require lower latency and the highest reliability at a premium price point." source

Retirements

Deprecated, still callable: Gemini 2.5 Flash (shutdown December 1, 2026); Gemini 2.5 Pro (shutdown December 1, 2026); Gemini Omni 1.1 Flash (shutdown December 3, 2026); Gemini 3.1 Flash-Lite (shutdown May 7, 2027); Gemini 3 Flash Preview (no shutdown date announced); Gemini 3.5 Flash (no shutdown date announced); Gemini 3.7 Flash (no shutdown date announced).

Retired: Gemini Omni Flash Preview (October 22, 2026), Gemini 2.5 Computer Use Preview (July 28, 2026), Gemini 2.0 Flash (June 1, 2026), Gemini 2.0 Flash-Lite (June 1, 2026), Gemini 3 Pro Preview (March 9, 2026).

Recorded price changes

Outside the table: Gemini Omni 1.2 Flash, Gemini Omni 1.1 Flash, Gemini Omni Flash Preview, priced per token but not with text output (2026-11-06).

Analysis that cites Google models

FAQ

What is the cheapest Gemini model on the API?

Gemini 2.5 Flash-Lite, at $0.10 per 1M input tokens and $0.40 per 1M output tokens, as Google's pricing page printed it on November 16, 2026.

How we checked

Full method: methodology. All providers: the full pricing table.