Gemini 3.5 Flash pricing & benchmarks
Released May 19, 2026 · served by 2 providers · ranked #15 by intelligence in our index
What Gemini 3.5 Flash is
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
- Model ID:
google/gemini-3.5-flash - Modality: text+image+file+audio+video->text
- Knowledge cutoff: 2025-01-01
- Tool calling: supported · Structured output: supported
Providers and prices for Gemini 3.5 Flash
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Googlecheapest | $2.70 | $16.20 | 1.0M | — | 98.1% | — |
| Google AI Studio | $2.70 | $16.20 | 1.0M | — | 100.0% | — |
Gemini 3.5 Flash benchmark results
Design Arena head-to-head results, as reported through the OpenRouter model API.
| Category | Arena | Rank | Elo | Win rate |
|---|---|---|---|---|
| agenticslides(python-pptx) | agents | #3 | 1242 | 57.8% |
| pptxslides | agents | #3 | 1244 | 57.7% |
| svg | models | #3 | 1297 | 62.2% |
| agenticslides | agents | #4 | 1244 | 57.5% |
| asciiart | models | #6 | 1299 | 60.9% |
| python-pptxslides | agents | #6 | 1247 | 57.4% |
| agentichtmlslides | agents | #7 | 1162 | 45.8% |
| agenticslides(html) | agents | #7 | 1162 | 45.7% |
| mobileapps | agents | #8 | 1247 | 55.3% |
| agenticgamedev | agents | #10 | 1188 | 53.9% |
| fullstack | agents | #10 | 1242 | 56.9% |
| gamedev | models | #12 | 1318 | 57.6% |
| webapps | agents | #12 | 1250 | 53.4% |
| androidnative | agents | #13 | 1219 | 51.6% |
| uicomponent | models | #14 | 1304 | 58.3% |
| htmlslides | agents | #15 | 1172 | 46.5% |
| 3d | models | #19 | 1294 | 57.7% |
| codecategories | models | #19 | 1289 | 56.7% |
| godotgamedev | agents | #21 | 1135 | 42.6% |
| website | models | #21 | 1283 | 55.9% |
| dataviz | models | #30 | 1256 | 54.3% |
Cheaper models in the same class
Models scoring within 4 points of Gemini 3.5 Flash on the Intelligence Index, but with a lower output price.
Compare Gemini 3.5 Flash head-to-head
FAQ
How much does the Gemini 3.5 Flash API cost?
$1.50 per 1M input tokens and $9.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $4.20.
Is Gemini 3.5 Flash free?
No. It is a paid model starting at $1.50 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Gemini 3.5 Flash?
Google at $2.70 input / $16.20 output per 1M tokens.
Can I self-host Gemini 3.5 Flash?
No. Gemini 3.5 Flash is closed-weight and only available through hosted APIs.