What the Gemini API costs. And the same models for 20 to 25% less.
Gemini's paid-tier prices per million tokens, from Google's pricing page, next to what the same model IDs cost on APIsRouter. Call them through the OpenAI SDK with one base URL.
The same traffic for 30 days
Tokens per request: chatbot 3,000 in (2,000 cached) and 500 out; extraction 1,500 in and 300 out; agent 68,000 in (60,000 cached) and 3,000 out.
| APIsRouter | ||
|---|---|---|
| Support chatbot, 1,000 answers a day (Gemini 3.8 Flash) | $83 | $67 |
| Document extraction, 10,000 pages a day (Gemini 3.1 Flash-Lite) | $248 | $198 |
| Coding agent, 200 tasks a day (Gemini 3.1 Pro Preview) | $384 | $297 |
| Total | $715 | $562 |
Gemini API prices, per million tokens
Google's paid tier, text models. Where APIsRouter sells a model below Google, both prices are shown. Google prices from ai.google.dev/gemini-api/docs/pricing, September 2026. Google's Gemini 3.1 Pro Preview and Gemini 2.5 Pro prices are for prompts up to 200,000 tokens.
| Model | Input: Google / APIsRouter | Cached input: Google / APIsRouter | Output: Google / APIsRouter |
|---|---|---|---|
| Gemini 3.8 Flash | $0.75 / $0.60 | $0.075 / $0.06 | $3.75 / $3 |
| Gemini 3.7 Flash | $0.75 / $0.60 | $0.075 / $0.06 | $3.75 / $3 |
| Gemini 3.6 Flash | $0.75 / $0.60 | $0.075 / $0.06 | $3.75 / $3 |
| Gemini 3.5 Flash | $1.50 / $1.20 | $0.15 / $0.12 | $9 / $7 |
| Gemini 3.1 Pro Preview | $2 / $1.50 | $0.20 / $0.15 | $12 / $9.50 |
| Gemini 3.1 Flash-Lite | $0.25 / $0.20 | $0.025 / $0.02 | $1.50 / $1.20 |
| Gemini 3 Flash Preview | $0.50 / $0.40 | $0.05 / $0.04 | $3 / $2.40 |
| Gemini 2.5 Flash | $0.30 / $0.24 | $0.03 / $0.024 | $2.50 / $2 |
| Gemini 3.5 Flash-Lite | $0.30 / Google's price only | $0.03 / Google's price only | $2.50 / Google's price only |
| Gemini 2.5 Pro | $1.25 / Google's price only | $0.125 / Google's price only | $10 / Google's price only |
| Gemini 2.5 Flash-Lite | $0.10 / Google's price only | $0.01 / Google's price only | $0.40 / Google's price only |
Free tier, paid tier and what changes
- Google's free tier: Most Gemini Flash models have a free tier in the Gemini API, with lower rate limits, and Google uses what you send to improve its products. Gemini 3.1 Pro Preview has no free tier.
- Introductory Flash prices end December 31, 2026: Gemini 3.8 Flash, Gemini 3.7 Flash and Gemini 3.6 Flash cost $0.75 / $3.75 per million input and output tokens on Google through December 31, 2026, and $1.50 / $7.50 from January 1.
- Long prompts cost more on Pro: Above 200,000 prompt tokens, Google charges $4 / $18 instead of $2 / $12 for Gemini 3.1 Pro Preview and $2.50 / $15 instead of $1.25 / $10 for Gemini 2.5 Pro, per million input and output tokens.
- Thinking tokens bill as output: Gemini models that think before they answer bill those tokens at the output price, so a short reply can still use many output tokens.
Switch with one line
- Get a key: Top up from $10 below. The key and a login link arrive by email.
- Point the OpenAI SDK at APIsRouter: Set base_url to https://api.apisrouter.com/v1. Model IDs are Google's, such as gemini-3.8-flash.
- Send requests: Every request shows up in your console with its tokens and cost.
from openai import OpenAI
client = OpenAI(
base_url="https://api.apisrouter.com/v1",
api_key="sk-your-apisrouter-key",
)
reply = client.chat.completions.create(
model="gemini-3.8-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)Two ways to pay
Both fill one balance, spent at the prices above. Pay as you go from $10 with no account, with +30% on the first top-up.
FAQ
How much does the Gemini API cost?
From $0.10 / $0.40 per million input and output tokens on Gemini 2.5 Flash-Lite to $2 / $12 on Gemini 3.1 Pro Preview, on Google's paid tier. Gemini 3.8 Flash costs $0.75 / $3.75 on Google and $0.60 / $3 on APIsRouter.
Is the Gemini API free?
Google has a free tier for most Flash models, with lower rate limits, and uses what you send to improve its products. Gemini 3.1 Pro Preview has no free tier. On APIsRouter you can start on a $2 trial credit: sign in and claim it from your dashboard, no card needed. After that you pay per token from $10, with +30% on the first top-up.
What is the cheapest Gemini model?
Gemini 2.5 Flash-Lite, at $0.10 / $0.40 per million input and output tokens on Google. On APIsRouter the cheapest is Gemini 3.1 Flash-Lite at $0.20 / $1.20.
Will Gemini Flash prices go up?
On Google, Gemini 3.8 Flash, Gemini 3.7 Flash and Gemini 3.6 Flash move from $0.75 / $3.75 to $1.50 / $7.50 per million input and output tokens on January 1.
Can I call Gemini with the OpenAI SDK?
Yes. Set base_url (baseURL in Node) to https://api.apisrouter.com/v1, use your APIsRouter key and Google's model IDs. Streaming and tool calls work through the same API.
Do I need a Google Cloud account?
No. One APIsRouter key calls Gemini, GPT, Claude, DeepSeek and the Nano Banana image models, all paid from one balance.