Cheap Gemini API — Pro and Flash from $0.12/1M
Gemini Pro and Flash at prices that make high-volume work sane — up to 100% below Google's official price. Both paths are open: the OpenAI-compatible endpoint for existing code, and Google's native generateContent when you need google_search grounding, long context or multimodal input the way Google ships it. Pay in ₽, USDT or by card.
Gemini API pricing
USD per 1M tokens, next to Google's official rate. Updated automatically from our live price list.
| Model | Input | Output | Savings | |
|---|---|---|---|---|
| Gemini 3.6 Flash | $0.42 | $2.80 | $0.75 | −44% |
| Gemini 3 Pro High | $0.47 | $2.80 | $2.00 | −77% |
| Gemini 3.1 Pro High | $0.47 | $2.80 | $2.00 | −77% |
| Gemini 3.1 Pro Low | $0.47 | $2.80 | $2.00 | −77% |
| Gemini 3.1 Pro Preview | $0.47 | $2.80 | $2.00 | −77% |
| Gemini 3.5 Flash | $0.35 | $2.10 | $1.50 | −77% |
| Gemini 3.7 Flash | $0.24 | $1.40 | $0.75 | −68% |
| Gemini 3.8 Flash | $0.24 | $1.40 | $0.83 | −71% |
| Gemini 3 Flash | $0.12 | $0.70 | $0.50 | −77% |
| Gemini 3 Flash Preview | $0.12 | $0.70 | $0.50 | −77% |
| Gemini 3.1 Flash Image | $0.02 / req | — | $0.50 | −100% |
| Gemini 3.1 Flash Image Preview | $0.02 / req | — | $0.50 | −100% |
Why take Gemini from here
Native endpoint for grounding
Besides the OpenAI-compatible path we proxy Google's own /v1beta generateContent. That matters: google_search grounding returns groundingMetadata with real sources only on the native route — through OpenAI-style function calling it silently disappears.
Flash tiers priced for volume
Classification, document parsing and high-frequency chat are where Gemini earns its keep. At these rates you can run them by the thousand without watching the meter.
No model swapping
response.model always equals what you asked for. We don't quietly route a request for the flagship to a cheaper tier — check the field yourself on any call.
How to connect Gemini
Any OpenAI SDK
Works in Cursor, Cline, Kilo Code, LangChain and anything else that lets you set a base URL.
from openai import OpenAI
client = OpenAI(
api_key="sk-...", # from cheapai.io/keys
base_url="https://cheapai.io/v1",
)Native Gemini endpoint
Use this one when you need google_search grounding — the OpenAI-compatible path loses groundingMetadata.
curl "https://cheapai.io/v1beta/models/gemini-3-flash:generateContent" \
-H "x-goog-api-key: sk-..." \
-H "Content-Type: application/json" \
-d '{"contents":[{"parts":[{"text":"hi"}]}],
"tools":[{"google_search":{}}]}'Also available without a CDN: https://api.cheapai.io/v1 — use it for long requests where the model stays silent over ~2 minutes, or where the CDN is unreachable.
Full guides for every tool: documentation →
FAQ
How much does the Gemini API cost here?
From $0.12 per 1M input tokens. 12 Gemini models are live right now and the table above is pulled from the same price list the billing uses, so it is never stale.
Is this the real Gemini, or a cheaper model behind the name?
The real thing. response.model always matches the model you requested, so you can verify it on any call without taking our word for it.
Does google_search grounding work?
It does, on the native /v1beta generateContent route — groundingMetadata with real sources comes back intact. Through the OpenAI-compatible path the tool is converted to function declarations and grounding is lost, which is a limitation of that format rather than of the gateway.
Do I need a VPN?
No. The domain and the API are reachable worldwide, and you can top up in ₽, USDT or by card.
Is there a subscription?
Not required. The default is pay-as-you-go from a balance that doesn't expire; monthly plans exist separately and give up to 40% off, but you never have to take one.