Google AI Studio — pricing & performance
Models served
23
of 908 tracked models
Mean output speed
129
tokens per second, averaged over
23 measured endpoints
23 measured endpoints
Mean latency
2.3s
time to first token, averaged over
23 measured endpoints
23 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
Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.
12 of 23 models ▾
☰⚙⇩
+Add model from specific provider
The Known Good
23 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 | 73 | 0.4s | 1.05M | |
|
Google: Gemini 2.5 Flash Lite
|
$0.050 | $0.20 | $0.087 | 153 | 0.4s | 1.05M | |
|
Google: Gemini 2.5 Pro
|
$0.62 | $5.00 | $1.72 | 118 | 3.4s | 1.05M | |
|
Google: Gemini 2.5 Pro Preview 05-06
|
$0.62 | $5.00 | $1.72 | 124 | 3.0s | 1.05M | |
|
Google: Gemini 2.5 Pro Preview 06-05
|
$0.62 | $5.00 | $1.72 | 124 | 3.0s | 1.05M | |
|
Google: Gemini 3 Flash Preview
|
$0.25 | $1.50 | $0.56 | 60 | 1.1s | 1.05M | |
|
Google: Gemini 3.1 Flash Lite
|
$0.12 | $0.75 | $0.28 | 144 | 1.2s | 1.05M | |
|
Google: Gemini 3.1 Flash Lite Preview
|
$0.12 | $0.75 | $0.28 | 120 | 0.4s | 1.05M | |
|
Google: Gemini 3.1 Pro Preview
|
$1.00 | $6.00 | $2.25 | 163 | 2.6s | 1.05M | |
|
Google: Gemini 3.1 Pro Preview Custom Tools
|
$2.00 | $12.00 | $4.50 | 86 | 2.3s | 1.05M | |
|
Google: Gemini 3.5 Flash
|
$0.75 | $4.50 | $1.69 | 205 | 1.5s | 1.05M | |
|
Google: Gemini 3.5 Flash Lite
|
$0.15 | $1.25 | $0.42 | 159 | 0.6s | 1.05M | |
|
Google: Gemini 3.6 Flash
|
$0.75 | $3.75 | $1.50 | 151 | 1.8s | 1.05M | |
|
Google: Gemma 4 26B A4B (free)
|
$0.000 | $0.000 | $0.000 | 31 | 0.9s | 262k | |
|
Google: Gemma 4 31B (free)
|
$0.000 | $0.000 | $0.000 | 29 | 1.3s | 262k | |
|
Google: Lyria 3 Clip Preview
|
$0.000 | $0.000 | $0.000 | 4 | 2.8s | 1.05M | |
|
Google: Lyria 3 Pro Preview
|
$0.000 | $0.000 | $0.000 | 5 | 7.0s | 1.05M | |
|
Google: Nano Banana (Gemini 2.5 Flash Image)
|
$0.15 | $1.25 | $0.42 | 205 | 0.4s | 33k | |
|
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
|
$0.50 | $3.00 | $1.12 | 164 | 6.7s | 66k | |
|
Google: Nano Banana 2 (Gemini 3.1 Flash Image)
|
$0.50 | $3.00 | $1.12 | 182 | 6.7s | 66k | |
|
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
|
$0.25 | $1.50 | $0.56 | 517 | 2.7s | 66k | |
|
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
|
$1.00 | $6.00 | $2.25 | 89 | 2.9s | 66k | |
|
Google: Nano Banana Pro (Gemini 3 Pro Image)
|
$2.00 | $12.00 | $4.50 | 68 | 0.1s | 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.