Google Gemini API
Google's Gemini 2.5 and 3.x family — fast, multimodal, with long context
Overview
Gemini is Google's flagship multimodal AI model family. Access Gemini 2.5 Flash, Gemini 2.5 Pro, Gemini 3 Flash, and Gemini 3 Pro through AI Generate with pay-per-token pricing and no monthly subscriptions.
All 10 Google Gemini variants & pricing
Every variant is accessible via the same API endpoint. Switch variants by changing the model parameter. No extra setup.
| Variant | Credits | Price USD | Unit | |
|---|---|---|---|---|
| Gemini 2.5 flash, Chat, Input | 18.00 | $0.1260 | per million tokens | Details → |
| Gemini 3 Flash, Chat, Input | 30.00 | $0.2100 | per million tokens | Details → |
| Gemini 2.5 Pro, Chat, Input | 76.00 | $0.5320 | per million tokens | Details → |
| Gemini 3.1 Pro- openai, chat, input | 100.00 | $0.7000 | per million | Details → |
| Gemini 3 Pro, Chat, Input | 100.00 | $0.7000 | per million tokens | Details → |
| Gemini 2.5 flash, Chat, Output | 150.00 | $1.0500 | per million tokens | Details → |
| Gemini 3 Flash, Chat, Output | 180.00 | $1.2600 | per million tokens | Details → |
| Gemini 2.5 Pro, Chat, Output | 600.00 | $4.2000 | per million tokens | Details → |
| Gemini 3 Pro, Chat, Output | 700.00 | $4.9000 | per million tokens | Details → |
| Gemini 3.1 Pro- openai, chat, output | 700.00 | $4.9000 | per million | Details → |
Use Google Gemini via API
Example call with the default variant. Replace model with any slug from the table above.
curl https://aimarcusimage.eu/api/v1/chat/completions \
-H "Authorization: Bearer sk-aig-..." \
-H "Content-Type: application/json" \
-d '{
"model": "google-gemini-2-5-flash-chat-input",
"messages": [
{
"role": "user",
"content": "Hello from AI Generate"
}
]
}'
FAQ
How much does Google Gemini cost?
Pricing starts at $0.1260 per million tokens for the most affordable variant. You pay per call from your credit balance — no monthly subscription, no minimum commitment. First $10 on signup are free.
Is this an official Google API?
AI Generate is an AI model aggregator that routes calls to Google's upstream API. You get the exact same model outputs with simpler billing (pay per call, no contracts), one API key for 288 models, and the same OpenAI-compatible request shape across all providers.
Can I use Google Gemini in production?
Yes. The endpoint is rate-limited to 20 requests per 10 seconds per API key, retries are idempotent via taskId, and async results are delivered via polling or webhook. Set a spend cap in dashboard settings to protect against runaway usage.
Which Google Gemini variant should I pick?
For first tests, start with the cheapest variant (lowest "Price USD" in the table above). Upgrade to higher-resolution or "Quality" tiers only when you have validated prompts. The Playground (free) lets you A/B test all variants before spending credits.