Call Gemini 2.5 Flash and Pro for free. The keys are OpenAI-compatible — copy one, set the base URL, and tap Gemini's huge context window and multimodal smarts. No Google account, no sign-up, no card.
A working API key that reaches Gemini 2.5 Flash
(gemini-2.5-flash) — and Pro where available — through an
OpenAI-compatible gateway. Gemini 2.5 shines with a very large context window
and multimodal input, making it great for long documents, summarization, and
fast general-purpose chat.
https://aiapiv2.pekpik.com/v1.gemini-2.5-flash with any OpenAI SDK or compatible tool.curl https://aiapiv2.pekpik.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_FREE_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-2.5-flash",
"messages": [{"role": "user", "content": "Summarize this article in 5 bullets"}]
}'from openai import OpenAI
client = OpenAI(
api_key="YOUR_FREE_KEY",
base_url="https://aiapiv2.pekpik.com/v1",
)
resp = client.chat.completions.create(
model="gemini-2.5-flash",
messages=[{"role": "user", "content": "Give me 3 ideas for a weekend project"}],
)
print(resp.choices[0].message.content)Yes. Keys are shared publicly with a pre-funded budget — no credit card, no sign-up. Because they're shared, a key may run out of budget; grab another from the table or come back later.
Gemini 2.5 Flash via gemini-2.5-flash, and Pro via gemini-2.5-pro where available. Keys are OpenAI-compatible — call them by changing the base URL.
Yes. Gemini 2.5 is known for very large context windows and multimodal capabilities — great for long documents and general chat.
Busy shared keys can hit a rate limit. Wait a moment, grab another key from the table, or use Smart mode in the playground, which auto-routes to an available model.