Google Gemini API vs OpenRouter: free tiers compared

Both columns come from each provider’s own pages, with the day each line was read. Where a page does not state a value, the cell says so.

Google Gemini API and OpenRouter free tiers side by side
Line	Google Gemini APIFree tier	OpenRouterFree tier
Free allowance	Not published Limits are per project and shown only inside Google AI Studio. 3 Oct	20 req/min · 50 req/day 1,000 req/day once the account has bought at least 10 credits. 3 Oct
Requests / min	Not published Not published per model: “Rate limits … can be viewed in Google AI Studio.” 3 Oct	20 All free model variants together. 3 Oct
Requests / day	Not published Not published per model: “Rate limits … can be viewed in Google AI Studio.” 3 Oct	50 1,000/day once the account has bought at least 10 credits. 3 Oct
Tokens / min	Not published Not published per model. 3 Oct	Not published The limits page counts requests, not tokens. 3 Oct
Tokens / day	Not published Not published per model. 3 Oct	Not published The limits page counts requests, not tokens. 3 Oct
Card to start	Not required The Free tier qualifies with an “Active project or free trial”; no billing tier is involved. 3 Oct	Not required The 50 req/day ceiling applies to accounts that bought fewer than 10 credits, so no purchase is needed. 3 Oct
Trains on your data	Yes On unpaid services, content is used “to provide, improve, and develop Google products”, and human reviewers may read it. 3 Oct	Your setting An account setting decides whether requests may be routed to providers that train on your data, with a separate switch for free models. 3 Oct
Commercial use	Restricted Only Paid Services may be used for API clients offered to users in the EEA, Switzerland or the UK. 3 Oct	Not verified
OpenAI SDK	Yes 3 Oct	Yes 3 Oct
Image input	Yes Gemini models take images natively. 3 Oct	Yes Several free variants list image input; see the free model list. 3 Oct

22 of 24 cells above were read on the provider’s own page in the last 30 days (oldest check: 3 Oct 2026). Each check mark opens that page. The other 2 say “not verified” instead of repeating a number from someone else’s article.

Where they differ

OpenRouter publishes its requests per minute (20); Google Gemini API does not publish that figure.
OpenRouter publishes its requests per day (50); Google Gemini API does not publish that figure.
Use of your prompts for training: Google Gemini API, yes; OpenRouter, your setting.
Google Gemini API commercial use: restricted. Only Paid Services may be used for API clients offered to users in the EEA, Switzerland or the UK.

Only differences confirmed on both sides are listed. We do not rank speed or output quality: this site does not measure them.

Same code for both

Both expose an OpenAI-compatible endpoint. Choose either provider below and compare the three values that change.

base_url: https://generativelanguage.googleapis.com/v1beta/openai/
model: gemini-3.8-flash
key from: $GEMINI_API_KEY

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
    api_key=os.environ["GEMINI_API_KEY"],
)

reply = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[{"role": "user", "content": "Reply with the word: ok"}],
)
print(reply.choices[0].message.content)

Endpoint read on 3 Oct 2026· ai.google.dev

The key is read from an environment variable on your machine. This site has no field for keys and never asks for one.

Other comparisons

Questions and answers

Which has the higher free limit, Google Gemini API or OpenRouter?

Google Gemini API: not published (Limits are per project and shown only inside Google AI Studio). OpenRouter: 20 req/min · 50 req/day. The units differ between providers, so compare them against your own traffic.

Do Google Gemini API and OpenRouter need a credit card?

Google Gemini API: not required. OpenRouter: not required.

Which one trains on my prompts?

Google Gemini API: yes. OpenRouter: your setting.

Can I use both with the same code?

Yes. Both expose an OpenAI-compatible endpoint: https://generativelanguage.googleapis.com/v1beta/openai/ and https://openrouter.ai/api/v1. Only the base URL, the model name and the key change.