Google AI Studio
Explore Google AI Studio models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Google AI Studiogoogle-ai-studio
No provider claim
| Provider | Google AI Studio |
|---|---|
| Provider website | https://ai.google.dev/ |
| Models | 12 public models |
| Prepaid routes | 12 |
| BYOK routes | 10 |
| Zero data retention | no |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | Not currently marked ZDR in TrustedRouter. Google AI Studio and the Gemini Developer API have product- and billing-specific data-use terms, so this route stays outside trustedrouter/zdr. Policy source |
Measured performance
60 samplesContinuously sampled across Google AI Studio's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1549 ms |
|---|---|
| Effective throughput | 29 tok/s n=2 |
| Uptime | 100.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemini-2.5-flash | 1549 ms | 1549 ms | — | 100.00% | — | 15 |
| google/gemini-3.1-flash-lite | 1810 ms | 1809 ms | — | 100.00% | — | 10 |
| google/gemini-3.5-flash-lite | 930 ms | 930 ms | — | 100.00% | — | 6 |
| google/gemini-3-flash-preview | 1140 ms | 1140 ms | — | 100.00% | — | 6 |
| google/gemini-3.5-flash | 1257 ms | 1257 ms | — | 100.00% | — | 6 |
| google/gemini-3.1-flash-image-preview | 1432 ms | 1431 ms | — | 100.00% | — | 7 |
| google/gemini-3.6-flash | 1846 ms | 1846 ms | — | 100.00% | — | 3 |
| google/gemini-3.7-flash | 1900 ms | 1900 ms | 22 tok/s n=1 | 100.00% | — | 5 |
| google/gemini-3.1-pro-preview | 3898 ms | 3897 ms | 37 tok/s n=1 | 100.00% | — | 2 |
Google AI Studio performance history · Full provider & model leaderboard.
Models served by Google AI Studio.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
google/gemini-2.5-flashGoogle: Gemini 2.5 Flash |
— | 1,048,576 | 2 | $0.3165/1M | $2.6375/1M | prepaid BYOK |
google/gemini-3-flash-previewGoogle: Gemini 3 Flash Preview |
IQ 116#32 | 1,048,576 | 2 | $0.5275/1M | $3.165/1M | prepaid BYOK |
google/gemini-3.1-flash-image-previewNano Banana 2 |
— | 65,536 | 2 | $0.5275/1M | $63.3/1M | prepaid BYOK |
google/gemini-3.1-flash-liteGoogle: Gemini 3.1 Flash Lite |
IQ 101#72 | 1,048,576 | 2 | $0.26375/1M | $1.5825/1M | prepaid BYOK |
google/gemini-3.1-pro-previewGoogle: Gemini 3.1 Pro Preview |
IQ 127#10 | 1,048,576 | 2 | $2.11/1M | $12.66/1M | prepaid BYOK |
google/gemini-3.5-flashGoogle: Gemini 3.5 Flash |
IQ 124#13 | 1,048,576 | 2 | $1.5825/1M | $9.495/1M | prepaid BYOK |
google/gemini-3.5-flash-liteGoogle: Gemini 3.5 Flash Lite |
IQ 108#52 | 1,048,576 | 2 | $0.3165/1M | $2.6375/1M | prepaid BYOK |
google/gemini-3.6-flashGoogle: Gemini 3.6 Flash |
IQ 123#14 | 1,048,576 | 2 | $0.79125/1M | $3.95625/1M | prepaid BYOK |
google/gemini-3.7-flashGoogle: Gemini 3.7 Flash |
IQ 122#17 | 1,048,576 | 2 | $0.79125/1M | $3.95625/1M | prepaid BYOK |
google/gemini-embedding-001Gemini Embedding 001 |
— | 2,048 | 2 | $0.15825/1M | selected route | prepaid BYOK |
google/veo-3.1Google Veo 3.1 |
— | 2,500 | 1 | selected route | selected route | prepaid |
google/veo-3.1-fastGoogle Veo 3.1 Fast |
— | 2,500 | 1 | selected route | selected route | prepaid |
Questions
Does Google AI Studio have zero data retention?
TrustedRouter does not currently mark Google AI Studio as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Google AI Studio end-to-end encrypted?
TrustedRouter does not currently mark Google AI Studio as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Google AI Studio models are available through TrustedRouter?
This page currently lists 12 public Google AI Studio models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.