Google Gemini API pricing: all 10 models, cheapest first
Google lists 10 Gemini models with a price on its official API pricing page, from Gemini 2.5 Flash-Lite at $0.1 input and $0.4 output per 1M tokens to Gemini 4 Carbon at $2 and $10 per 1M. Every rate below is checked 2026-11-18, links to its model page and names the official source.
All 10 Gemini models, cheapest first
| Model | Input /1M | Cached /1M | Output /1M | 1,000 calls (10K in / 1K out) | Checked |
|---|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.1 | $0.01 | $0.4 | $0.0014 | 2026-11-15 |
| Gemini 3.1 Flash-Lite | $0.25 | $0.025 | $1.5 | $0.0040 | 2026-11-15 |
| Gemini 3.5 Flash-Lite | $0.3 | $0.03 | $2.5 | $0.0055 | 2026-11-15 |
| Gemini 2.5 Flash | $0.3 | $0.03 | $2.5 | $0.0055 | 2026-11-15 |
| Gemini 3.8 Flash | $0.75 | $0.075 | $3.75 | $0.0112 | 2026-11-15 |
| Gemini 3.6 Flash | $0.75 | $0.075 | $3.75 | $0.0112 | 2026-11-15 |
| Gemini 2.5 Pro | $1.25 | $0.125 | $10 | $0.0225 | 2026-11-15 |
| Gemini 4 Carbon | $2 | $0.1 | $10 | $0.0300 | 2026-11-15 |
| Gemini 4 Argon | $2 | $0.1 | $10 | $0.0300 | 2026-11-15 |
| Gemini 3.1 Pro Preview | $2 | $0.2 | $12 | $0.0320 | 2026-11-15 |
Prices are the standard list rate per 1M tokens on the official Google pricing page, checked 2026-11-18. The 1,000-call column uses a 10,000-input / 1,000-output workload with no caching; price your own token shape in the Gemini calculator.
What the price range means
Across the 10 Google models priced here, 1M input tokens cost $0.1 to $2 (a 20.0x spread) and 1M output tokens cost $0.4 to $12. The cheapest input rate is Gemini 2.5 Flash-Lite at $0.1 per 1M; the highest is Gemini 4 Carbon at $2. At a 10,000-input / 1,000-output workload the cheapest model here costs $0.0014 per 1,000 calls and the most expensive costs $0.0320.
Input and output are priced separately, so the order changes with the workload: a model with a low input rate climbs a RAG-style table, while a model with a low output rate climbs a long-answer table. The table above holds one fixed shape (10,000 in / 1,000 out) so the rows are directly comparable; price your own shape in the Gemini API cost calculator or the homepage calculator.
10 of the 10 models list a separate cached-input rate; where a model does not, this table reuses its standard input rate and shows a dash.
How Google bills tokens
Google publishes a per-token list price for every model in the table: input, output and, for 10 of them, a cheaper cached-input rate. The rate applies per 1M tokens; the method page explains how a price is read from the official page and what happens when one cannot be verified.
Batch requests are billed at half the standard rate for 10 of these models (Gemini 2.5 Flash-Lite, Gemini 3.1 Flash-Lite, Gemini 3.5 Flash-Lite, Gemini 2.5 Flash and others). Batch only pays off for work nobody is waiting on.
2 models move to a higher long-context rate once the prompt passes a token threshold: Gemini 2.5 Pro over 200K input, Gemini 3.1 Pro Preview over 200K input. Above that threshold the higher rate applies to the whole request, not just to the excess tokens.
Context windows run from 1049K tokens on Gemini 2.5 Flash-Lite to 1049K on Gemini 2.5 Flash-Lite. A request larger than the window is rejected, so a long-document workload has to be split or moved to a larger-context model; that changes the number of calls, not just the rate.
Which Gemini model to price first
Start with the cheapest model that passes your own test, not with the most expensive one. Gemini 2.5 Flash-Lite has the lowest input rate in this lineup at $0.1 per 1M tokens; if its answers hold up on your prompts, moving a workload down to it is usually worth more than any caching or batch tweak. If it fails, step up one row at a time in the table above and re-run the same prompts, so the quality difference you pay for is one you can see.
Cost per call is not the same as cost per finished task: a cheaper model that needs two attempts, a longer prompt or manual fixes costs more than its rate suggests. The benchmark comparison puts measured scores next to these prices, and the coding-cost ranking prices completed coding tasks rather than single calls.
Related
- Gemini API cost calculator
- Every model price per 1M tokens
- Cheapest LLM APIs, ranked by cost per call
- Models grouped by price tier
- Blended cost by input:output mix
- GPT-6.1 Sol vs Gemini 4 Argon
- Claude Sonnet 5.5 vs Gemini 4 Argon
- GPT-5.4 mini vs Gemini 3.8 Flash
- OpenAI models and prices
- Anthropic models and prices
- xAI models and prices
- DeepSeek models and prices
- Mistral models and prices
Questions
How many Google models does this page price?
This page prices 10 Google models, every one copied from the official Google pricing page and checked 2026-11-18. Each row links to a per-model page with the full rate tiers, worked examples and the source URL, so a number here can always be traced back.
Does Google charge less for cached input tokens?
Yes. 10 of the 10 models list a cached-input rate below the standard input rate; the cheapest cached read here is $0.01 per 1M tokens. Cached pricing only applies to a repeated prefix the provider has stored, so the saving depends on how much of your prompt is identical between calls.
Which Google model is cheapest per 1M tokens?
Gemini 2.5 Flash-Lite has the lowest input rate at $0.1 per 1M tokens and $0.4 per 1M output tokens. At a 10,000-input / 1,000-output workload the cheapest model is Gemini 2.5 Flash-Lite at $0.0014 per 1,000 calls, while Gemini 4 Carbon at $2/$10 carries the highest input rate in this lineup.
Which Google model has the largest context window?
The largest context window here is 1049K tokens on Gemini 2.5 Flash-Lite. A larger window does not make a model cheaper: cost the input side of the bill first and check the window only for the documents you need to send in one request.
Next step → Price a Gemini workload per user
Price data last checked 2026-11-18 against official sources · how we verify
Price-change alerts
One short email when a provider changes a price or a promo ends. No spam, unsubscribe any time.