Gemini API pricing: what Google charges per 1M tokens
Paid-tier input, output and context-caching prices for Google’s current Gemini text models, the dated price changes, long-prompt rates, batch pricing and a worked monthly cost example.
Last updated October 22, 2026
How much does the Gemini API cost?
On October 22, 2026, Gemini 4 Argon cost $2 per 1M input tokens and $10 per 1M output tokens through November 30, 2026, rising to $4 and $20 on December 1. Gemini 3.8 Flash cost $0.75 and $3.75 through 2026, and Gemini 2.5 Flash-Lite $0.10 and $0.40. The Batch API halves prices.
What does each Gemini model cost per 1M tokens?
These are Standard, paid-tier prices for the Gemini text models on Google’s Gemini Developer API pricing page. Where Google lists a separate audio price, the input price shown is for text, image and video. Context caching is the price per 1M cached tokens read; some models also charge an hourly storage price for cached tokens.
| Model | Input | Output (including thinking) | Context caching | Notes |
|---|---|---|---|---|
| Gemini 4 Argon (gemini-4-argon) | $2.00 through Nov 30, 2026; $4.00 from Dec 1, 2026 | $10.00; $20.00 from Dec 1, 2026 | $0.10; $0.20 from Dec 1, 2026 | Implicit caching only; not on the free tier |
| Gemini 3.8 Flash (gemini-3.8-flash) | $0.75 through Dec 31, 2026; $1.50 from Jan 1, 2027 | $3.75; $7.50 from Jan 1, 2027 | $0.075; $0.15 from Jan 1, 2027 | Storage $0.50 per 1M tokens per hour ($1.00 from Jan 1, 2027) |
| Gemini 3.6 Flash (gemini-3.6-flash) | $0.75 through Dec 31, 2026; $1.50 from Jan 1, 2027 | $3.75; $7.50 from Jan 1, 2027 | $0.075; $0.15 from Jan 1, 2027 | Google calls it the previous-generation Flash model |
| Gemini 3.1 Pro Preview (gemini-3.1-pro-preview) | $2.00 (prompts up to 200K tokens); $4.00 (over 200K) | $12.00; $18.00 over 200K | $0.20; $0.40 over 200K | Storage $4.50 per 1M tokens per hour; not on the free tier |
| Gemini 3.5 Flash-Lite (gemini-3.5-flash-lite) | $0.30 | $2.50 | $0.03 | Storage $1.00 per 1M tokens per hour |
| Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite) | $0.25 ($0.50 audio) | $1.50 | $0.025 ($0.05 audio) | Storage $1.00 per 1M tokens per hour |
| Gemini 3 Flash Preview (gemini-3-flash-preview) | $0.50 ($1.00 audio) | $3.00 | $0.05 ($0.10 audio) | Google calls it its legacy Flash model |
| Gemini 2.5 Pro (gemini-2.5-pro) | $1.25 (prompts up to 200K tokens); $2.50 (over 200K) | $10.00; $15.00 over 200K | $0.125; $0.25 over 200K | Storage $4.50 per 1M tokens per hour |
| Gemini 2.5 Flash (gemini-2.5-flash) | $0.30 ($1.00 audio) | $2.50 | $0.03 ($0.10 audio) | Storage $1.00 per 1M tokens per hour |
| Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite) | $0.10 ($0.30 audio) | $0.40 | $0.01 ($0.03 audio) | Storage $1.00 per 1M tokens per hour |
Prices checked October 22, 2026. Providers change prices often; confirm on Google’s Gemini API pricing page.
The same page prices Google’s live audio, speech, image, video, embedding and robotics models separately; they are not included here.
How does Gemini API billing work?
- Free and paid tiers. Google lists a free tier for developers getting started, with free tokens on many models, and a paid tier with higher rate limits, context caching and the Batch API. The page says free-tier content is used to improve Google’s products and paid-tier content is not.
- Input and output are billed separately. Output prices include thinking tokens. Some models charge more for audio input than for text, image and video.
- Long prompts can cost more. On Gemini 3.1 Pro Preview and Gemini 2.5 Pro, prompts over 200K tokens are billed at higher input, output and caching rates.
- Documents count as images. Google says PDF and other document tokens are billed at the image token rate.
- Grounding costs extra. For Gemini 3 and newer models, Grounding with Google Search includes 5,000 free requests a month shared across those models, then $14 per 1,000 requests.
- Tiers change the rate. Besides Standard, Google lists Batch, Flex and Priority tiers; Priority costs more (Gemini 4 Argon is $3.60 input and $18.00 output through November 30, 2026).
What would 1M requests a month cost on Gemini?
Take 1,000,000 requests a month, each with 1,000 input tokens and 300 output tokens: 1,000M input tokens and 300M output tokens of text, on the paid tier with no caching.
Monthly cost = 1,000 × input price + 300 × output price (prices per 1M tokens)
| Model and period | Calculation | Monthly cost |
|---|---|---|
| Gemini 4 Argon, through Nov 30, 2026 | 1,000 × $2.00 + 300 × $10.00 | $5,000 |
| Gemini 4 Argon, from Dec 1, 2026 | 1,000 × $4.00 + 300 × $20.00 | $10,000 |
| Gemini 3.8 Flash, through Dec 31, 2026 | 1,000 × $0.75 + 300 × $3.75 | $1,875 |
| Gemini 3.8 Flash, from Jan 1, 2027 | 1,000 × $1.50 + 300 × $7.50 | $3,750 |
| Gemini 2.5 Flash-Lite | 1,000 × $0.10 + 300 × $0.40 | $220 |
The scheduled changes double the bill for the same traffic, so plan with the later price if you are committing to a model. Count your real prompt sizes with the token calculator.
How can you cut your Gemini API bill?
| Model | Batch input | Batch output |
|---|---|---|
| Gemini 4 Argon | $1.00 through Nov 30, 2026; $2.00 from Dec 1, 2026 | $5.00; $10.00 from Dec 1, 2026 |
| Gemini 3.8 Flash | $0.375 through Dec 31, 2026; $0.75 from Jan 1, 2027 | $1.875; $3.75 from Jan 1, 2027 |
| Gemini 3.1 Pro Preview | $1.00 (up to 200K); $2.00 (over 200K) | $6.00; $9.00 over 200K |
| Gemini 3.5 Flash-Lite | $0.15 | $1.25 |
| Gemini 3.1 Flash-Lite | $0.125 | $0.75 |
| Gemini 2.5 Pro | $0.625 (up to 200K); $1.25 (over 200K) | $5.00; $7.50 over 200K |
| Gemini 2.5 Flash | $0.15 | $1.25 |
| Gemini 2.5 Flash-Lite | $0.05 | $0.20 |
Prices checked October 22, 2026. Providers change prices often; confirm on Google’s Gemini API pricing page.
- Batch API. Google’s pricing page describes the Batch API as a 50% cost reduction, and the table above shows it on every model listed.
- Flex tier. Google also lists a Flex tier; on Gemini 4 Argon, Gemini 3.8 Flash and Gemini 2.5 Pro it is priced the same as Batch.
- Context caching. Cached tokens are billed at the context caching price, 5% to 10% of the input price on the models above, plus hourly storage on models that list it. Gemini 4 Argon supports implicit caching only.
- Smaller models. Gemini 2.5 Flash-Lite costs 1/20 of Gemini 4 Argon’s current input price. Route simple, high-volume requests to a Flash-Lite model.
- The free tier for testing. Prototype on the free tier where a model offers it, keeping in mind the data-use difference.
To estimate what response caching and model routing could save on your traffic, try the LLM gateway savings calculator.
How does Perimattic LLM Gateway help with Gemini costs?
Perimattic LLM Gateway sits between your application and model providers. Its features:
- One OpenAI-compatible API in front of Google, OpenAI, Anthropic, Mistral, DeepSeek and open models, so moving off a model before a price rise is a configuration change.
- Routing rules that send each request to a model by cost, latency or task, with automatic fallback when a provider errors or rate-limits.
- Exact-match and semantic caching of responses.
- Budgets and rate limits per team, API key or customer, with cost tracking and alerts.
Get started: Sign up and our team will walk you through Perimattic LLM Gateway for your workloads.
Where do these Gemini prices come from?
All prices on this page come from Google’s Gemini Developer API pricing page (last updated October 19, 2026, according to the page). They are paid-tier prices in US dollars, before tax. Google notes that prices on Gemini Enterprise Agent Platform may differ. Prices checked October 22, 2026; providers change prices often — confirm on the provider’s page before you rely on them. Perimattic is not affiliated with Google.
Compare Gemini with other providers
Gemini API pricing, answered
Is the Gemini API free?
Partly. Google’s pricing page lists a free tier with free input and output tokens on many models, such as Gemini 3.8 Flash and Gemini 2.5 Flash-Lite, but not on Gemini 4 Argon or Gemini 3.1 Pro Preview. On the free tier, the page says content is used to improve Google’s products; on the paid tier it is not. Free-tier rate limits are lower.
Why are some Gemini prices changing?
Google’s pricing page lists dated prices for some models: Gemini 4 Argon’s rates double on December 1, 2026, and Gemini 3.8 Flash and Gemini 3.6 Flash rates double on January 1, 2027. Budget for the later price if your project runs past those dates.
Do Gemini thinking tokens cost extra?
They are billed as output. Google’s pricing tables label the output price “including thinking tokens”, so a model that reasons at length before answering uses more output tokens and costs more per request.
Want one API for every model, with costs under control?
Sign up to tell us which models and providers you use, and our team will get in touch to set up the LLM Gateway for your stack.
Sign up