Models / Gemini pricing
Gemini API pricing
11 Gemini models from Google on one key, per million tokens. Input 40% to 70% under Google's list price, output 40% to 70%. Lowest price: Gemini 3.1 Flash Lite Preview, $0.15 in and $0.90 out.
Prices · per million tokens, USD, next to Google's list price
| Model | Input | Cached input | Output | Under list |
|---|---|---|---|---|
| Gemini 4 Argongemini-4-argon | $0.60list $2.00 | $0.06list $0.10 | $3.00list $10.00 | 70% in · 70% out |
| Gemini 3.8 Flashgemini-3.8-flash | $0.45list $0.75 | $0.045list $0.075 | $2.25list $3.75 | 40% in · 40% out |
| Gemini 3.5 Flashgemini-3.5-flash | $0.90list $1.50 | $0.09list $0.15 | $5.40list $9.00 | 40% in · 40% out |
| Gemini 3.1 Pro Previewgemini-3.1-pro-preview | $1.20list $2.00 | $0.12list $0.20 | $7.20list $12.00 | 40% in · 40% out |
| Gemini 3.7 Flashgemini-3.7-flash | $0.45list $0.75 | $0.045list $0.075 | $2.25list $3.75 | 40% in · 40% out |
| Gemini 3.6 Flashgemini-3.6-flash | $0.45list $0.75 | $0.045list $0.075 | $2.25list $3.75 | 40% in · 40% out |
| Gemini 3.5 Flash Litegemini-3.5-flash-lite | $0.18list $0.30 | $0.018list $0.03 | $1.50list $2.50 | 40% in · 40% out |
| Gemini 3.1 Flash Lite Previewgemini-3.1-flash-lite-preview | $0.15list $0.25 | $0.015list $0.025 | $0.90list $1.50 | 40% in · 40% out |
| Gemini 3 Flash Previewgemini-3-flash-preview | $0.30list $0.50 | $0.03list $0.05 | $1.80list $3.00 | 40% in · 40% out |
| Gemini 2.5 Flashgemini-2.5-flash | $0.18list $0.30 | $0.018list $0.03 | $1.50list $2.50 | 40% in · 40% out |
| Gemini 2.5 Progemini-2.5-pro | $0.75list $1.25 | $0.075list $0.125 | $6.00list $10.00 | 40% in · 40% out |
List price: Google's published rate, read October 2026. Live from GET https://api.uplinkswitch.com/v1/catalog.
Call them · same base URL and key for every model
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="gemini-4-argon",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'gemini-4-argon',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);Questions
- Which Gemini model costs the least?
- Gemini 3.1 Flash Lite Preview (gemini-3.1-flash-lite-preview): $0.15 per million input tokens and $0.90 per million output tokens.
- How far under Google's list price is it?
- Input runs 40% to 70% under Google's list price, output 40% to 70%, depending on the model. Each row above shows both prices.
- Is there a subscription?
- No. Prepaid credit from $10, with no subscription or monthly fee. Each top-up locks your prices for 30 days.
- How is cached input billed?
- At the cached rate in the table. A model with no cached rate bills cached tokens at its input rate.
- Are there rate limits?
- Every key carries a request-per-minute limit and a concurrency limit.