Google AI Studio — pricing & performance
Models served
25
of 1,094 tracked models
Mean output speed
120
tokens per second, averaged over
25 measured endpoints
25 measured endpoints
Mean latency
2.6s
time to first token, averaged over
25 measured endpoints
25 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Google AI Studio
Output tokens per second for all 25 models on Google AI Studio with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
The Known Good
25 models on Google AI Studio
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Google: Gemini 2.5 Flash
|
$0.15 | $1.25 | $0.42 | 269 | 0.6s | 1.05M | |
|
Google: Gemini 2.5 Flash Lite
|
$0.050 | $0.20 | $0.087 | 173 | 0.6s | 1.05M | |
|
Google: Gemini 2.5 Pro
|
$0.62 | $5.00 | $1.72 | 103 | 3.7s | 1.05M | |
|
Google: Gemini 2.5 Pro Preview 05-06
|
$0.62 | $5.00 | $1.72 | 103 | 3.7s | 1.05M | |
|
Google: Gemini 2.5 Pro Preview 06-05
|
$0.62 | $5.00 | $1.72 | 102 | 3.6s | 1.05M | |
|
Google: Gemini 3 Flash Preview
|
$0.25 | $1.50 | $0.56 | 72 | 1.3s | 1.05M | |
|
Google: Gemini 3.1 Flash Lite
|
$0.12 | $0.75 | $0.28 | 99 | 0.6s | 1.05M | |
|
Google: Gemini 3.1 Flash Lite Preview
|
$0.12 | $0.75 | $0.28 | 107 | 0.7s | 1.05M | |
|
Google: Gemini 3.1 Pro Preview
|
$1.00 | $6.00 | $2.25 | 111 | 3.2s | 1.05M | |
|
Google: Gemini 3.1 Pro Preview Custom Tools
|
$2.00 | $12.00 | $4.50 | 72 | 3.1s | 1.05M | |
|
Google: Gemini 3.5 Flash
|
$0.75 | $4.50 | $1.69 | 187 | 1.6s | 1.05M | |
|
Google: Gemini 3.5 Flash Lite
|
$0.15 | $1.25 | $0.42 | 90 | 0.4s | 1.05M | |
|
Google: Gemini 3.6 Flash
|
$0.38 | $1.88 | $0.75 | 130 | 1.9s | 1.05M | |
|
Google: Gemini 3.7 Flash
|
$0.38 | $1.88 | $0.75 | 170 | 1.5s | 1.05M | |
|
Google: Gemini 3.8 Flash
|
$0.38 | $1.88 | $0.75 | 190 | 2.9s | 1.05M | |
|
Google: Gemma 4 26B A4B (free)
|
$0.000 | $0.000 | $0.000 | 33 | 0.9s | 262k | |
|
Google: Gemma 4 31B (free)
|
$0.000 | $0.000 | $0.000 | 27 | 1.3s | 262k | |
|
Google: Lyria 3 Clip Preview
|
$0.000 | $0.000 | $0.000 | 7 | 3.5s | 1.05M | |
|
Google: Lyria 3 Pro Preview
|
$0.000 | $0.000 | $0.000 | 1 | 5.9s | 1.05M | |
|
Google: Nano Banana (Gemini 2.5 Flash Image)
|
$0.15 | $1.25 | $0.42 | 225 | 0.4s | 33k | |
|
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
|
$0.50 | $3.00 | $1.12 | 135 | 10.6s | 66k | |
|
Google: Nano Banana 2 (Gemini 3.1 Flash Image)
|
$0.50 | $3.00 | $1.12 | 145 | 8.2s | 66k | |
|
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
|
$0.25 | $1.50 | $0.56 | 321 | 0.5s | 66k | |
|
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
|
$1.00 | $6.00 | $2.25 | 69 | 3.9s | 66k | |
|
Google: Nano Banana Pro (Gemini 3 Pro Image)
|
$2.00 | $12.00 | $4.50 | 53 | 0.3s | 131k |
The Known Good
Source. Prices, endpoint availability and throughput for Google AI Studio are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.